Tootfinder

Deep Learning Model Acceleration and Optimization Strategies for Real-Time Recommendation Systems
Junli Shao, Jing Dong, Dingzhou Wang, Kowei Shih, Dannier Li, Chengrui Zhou
https://arxiv.org/abs/2506.11421

Deep Learning Model Acceleration and Optimization Strategies for Real-Time Recommendation Systems
With the rapid growth of Internet services, recommendation systems play a central role in delivering personalized content. Faced with massive user requests and complex model architectures, the key challenge for real-time recommendation systems is how to reduce inference latency and increase system throughput without sacrificing recommendation quality. This paper addresses the high computational cost and resource bottlenecks of deep learning models in real-time settings by proposing a combined s…

My largest remaining NSF grant, which was awarded by a competitive process on the recommendation of national experts, was terminated yesterday. The money would have paid for PhD students to invent better AI systems for everyday people who need programs written for them but can't or won't write them themselves. I'm sad that the rate of progress we make will slow down significantly, because all our progress is made public for everyone to benefit from. That's what

#NowPlaying - picked up a copy of mike heron's "smiling men with bad reputations" after overhearing the below recommendation at the @… record fair. besides the occasional r&b & semi-zep moves, can feel that

Generative Representational Learning of Foundation Models for Recommendation
Zheli Zhou, Chenxu Zhu, Jianghao Lin, Bo Chen, Ruiming Tang, Weinan Zhang, Yong Yu
https://arxiv.org/abs/2506.11999

Generative Representational Learning of Foundation Models for Recommendation
Developing a single foundation model with the capability to excel across diverse tasks has been a long-standing objective in the field of artificial intelligence. As the wave of general-purpose foundation models sweeps across various domains, their influence has significantly extended to the field of recommendation systems. While recent efforts have explored recommendation foundation models for various generative tasks, they often overlook crucial embedding tasks and struggle with the complexit…

I started discovering @… last week by writing a #Kotlin recipe that moves Kotlin files according to the official directory structure recommendation. I mentioned some future works, and here they are. In this post, I want to describe how to compute the root packag…

A Transfer Learning Framework for Multilayer Networks via Model Averaging
Yongqin Qiu, Xinyu Zhang
https://arxiv.org/abs/2506.12455 https://

A Transfer Learning Framework for Multilayer Networks via Model Averaging
Link prediction in multilayer networks is a key challenge in applications such as recommendation systems and protein-protein interaction prediction. While many techniques have been developed, most rely on assumptions about shared structures and require access to raw auxiliary data, limiting their practicality. To address these issues, we propose a novel transfer learning framework for multilayer networks using a bi-level model averaging method. A $K$-fold cross-validation criterion based on edg…

BanditWare: A Contextual Bandit-based Framework for Hardware Prediction
Tain\~a Coleman, Hena Ahmed, Ravi Shende, Ismael Perez, \"Ilkay Altinta\c{s}
https://arxiv.org/abs/2506.13730

BanditWare: A Contextual Bandit-based Framework for Hardware Prediction
Distributed computing systems are essential for meeting the demands of modern applications, yet transitioning from single-system to distributed environments presents significant challenges. Misallocating resources in shared systems can lead to resource contention, system instability, degraded performance, priority inversion, inefficient utilization, increased latency, and environmental impact. We present BanditWare, an online recommendation system that dynamically selects the most suitable ha…

❓ for privacy-minded folks- anyone have a recommendation for a scale that measures more than weight (ex. muscle mass, fat %) but is also privacy-protecting?
And ideally has an “app” or interface that can track the info, see trends over time, etc.
Many choices online… but I have no idea where they are sending data (or to whom they are selling it).
Most private option of course is a scale that keeps all data local, but there is convenience in an app that easily tracks data, s…

Beyond Personalization: Federated Recommendation with Calibration via Low-rank Decomposition
Jundong Chen, Honglei Zhang, Haoxuan Li, Chunxu Zhang, Zhiwei Li, Yidong Li
https://arxiv.org/abs/2506.09525

Beyond Personalization: Federated Recommendation with Calibration via Low-rank Decomposition
Federated recommendation (FR) is a promising paradigm to protect user privacy in recommender systems. Distinct from general federated scenarios, FR inherently needs to preserve client-specific parameters, i.e., user embeddings, for privacy and personalization. However, we empirically find that globally aggregated item embeddings can induce skew in user embeddings, resulting in suboptimal performance. To this end, we theoretically analyze the user embedding skew issue and propose Personalized Fe…

Unterzeichnet das hier Mal bitte! Es gibt Bestrebungen, dass Leute mit Solaranlagen Netzentgelte bezahlen sollen. Das wäre der Tod der dezentralen Stromproduktion.
https://

Finger weg von der Photovoltaik!
Was genau plant die Bundesnetzagentur? Die Bundesnetzagentur stellt in einem offiziellen Diskussionspapier sechs Modelle zur Debatte, wie private Einspeiser künftig Netzentgelte zahlen sollen – also eine Art Gebühr für jede eingespeiste Kilowattstunde oder bereitgestellte Leistung. Auch Bestandsanlagen sind hier betroffen! Viele dieser Modelle sind nicht nur unsozial und unplanbar – sie sind auch energiewirtschaftlich kontraproduktiv. Denn: Sie bieten wenig Anreiz, PV-Anlagen und Speich…

lastfm_aminer: Last.fm social graph
This network contains the social graph of last.fm, a site that provides a streaming radio service, where users can search music and get personalized recommendation. A directed edge (i,j) means that user i follows user j.
This network has 136409 nodes and 1685524 edges.
Tags: Social, Online, Unweighted

Secretary of State Marco Rubio is pushing to 🆘 investigate whether Harvard University violated federal sanctions by collaborating on a health insurance conference in China that may have included officials blacklisted by the U.S. government.
Rubio signed off on a recommendation to the Treasury Department last month to open an investigation,
which experts and former Treasury officials said was 👉an unusual attempt from a cabinet secretary to target a domestic entity for sanctions enf…

Rubio Is Pressing to Open Sanctions Investigation Into Harvard
Experts and former officials said it was unusual for a cabinet secretary to try to influence the Treasury Department’s sanctions process to target a domestic entity.

User Altruism in Recommendation Systems
Ekaterina Fedorova, Madeline Kitch, Chara Podimata
https://arxiv.org/abs/2506.04525 https://a…

User Altruism in Recommendation Systems
Users of social media platforms based on recommendation systems (RecSys) (e.g. TikTok, X, YouTube) strategically interact with platform content to influence future recommendations. On some such platforms, users have been documented to form large-scale grassroots movements encouraging others to purposefully interact with algorithmically suppressed content in order to "boost" its recommendation; we term this behavior user altruism. To capture this behavior, we study a game between users and a Rec…

I saw a recommendation from Robin Hobb about the first book of the Murderbot series by @… yesterday and since I was between books I jumped right in.
Having read the first one I am excited to keep going. Funniest sci-fi I've read in years.
#SciFi

Context-Adaptive Graph Neural Networks for Next POI Recommendation
Yu Lei, Limin Shen, Zhu Sun, Tiantian He, Yew-Soon Ong
https://arxiv.org/abs/2506.10329 …

Context-Adaptive Graph Neural Networks for Next POI Recommendation
Next Point-of-Interest (POI) recommendation is a critical task in location-based services, aiming to predict users' next visits based on their check-in histories. While many existing methods leverage Graph Neural Networks (GNNs) to incorporate collaborative information and improve recommendation accuracy, most of them model each type of context using separate graphs, treating different factors in isolation. This limits their ability to model the co-influence of multiple contextual factors on us…

Dual-View Disentangled Multi-Intent Learning for Enhanced Collaborative Filtering
Shanfan Zhang, Yongyi Lin, Yuan Rao, Chenlong Zhang
https://arxiv.org/abs/2506.11538

Dual-View Disentangled Multi-Intent Learning for Enhanced Collaborative Filtering
Disentangling user intentions from implicit feedback has become a promising strategy to enhance recommendation accuracy and interpretability. Prior methods often model intentions independently and lack explicit supervision, thus failing to capture the joint semantics that drive user-item interactions. To address these limitations, we propose DMICF, a unified framework that explicitly models interaction-level intent alignment while leveraging structural signals from both user and item perspectiv…

“The String… will be much faster”
my brain is breaking https://mastodon.social/@Catfish_Man/114655168110161214

23andMe privacy ombudsman recommends company obtains consent for sale of customer data https://therecord.media/23andme-privacy-ombudsman-recommends-consent-sale

Building a Recommendation System Using Amazon Product Co-Purchasing Network
Minghao Liu, Catherine Zhao, Nathan Zhou
https://arxiv.org/abs/2506.02482 https…

Building a Recommendation System Using Amazon Product Co-Purchasing Network
This project develops an online, inductive recommendation system for newly listed products on e-commerce platforms, focusing on suggesting relevant new items to customers as they purchase other products. Using the Amazon Product Co-Purchasing Network Metadata dataset, we construct a co-purchasing graph where nodes represent products and edges capture co-purchasing relationships. To address the challenge of recommending new products with limited information, we apply a modified GraphSAGE method …

(2020) Want to reduce the carbon footprint of your food? Focus on what you eat, not whether your food is local #environment

You want to reduce the carbon footprint of your food? Focus on what you eat, not whether your food is local
“Eat local” is a common recommendation to reduce the carbon footprint of your diet. How does the impact of what you eat compare to where it's come from?

Replaced article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
Towards Robust Recommendation: A Review and an Adversarial Robustness Evaluation Library

Top CDC COVID vaccine adviser resigns following RFK Jr. recommendation change (Nathaniel Weixel/The Hill)
https://thehill.com/policy/healthcare/5333478-cdc-covid-vaccine-official-resigns/
http://www.memeorandum.com/250604/p167#a250604p167

LEANN: A Low-Storage Vector Index
Yichuan Wang, Shu Liu, Zhifei Li, Yongji Wu, Ziming Mao, Yilong Zhao, Xiao Yan, Zhiying Xu, Yang Zhou, Ion Stoica, Sewon Min, Matei Zaharia, Joseph E. Gonzalez
https://arxiv.org/abs/2506.08276

LEANN: A Low-Storage Vector Index
Embedding-based search is widely used in applications such as recommendation and retrieval-augmented generation (RAG). Recently, there is a growing demand to support these capabilities over personal data stored locally on devices. However, maintaining the necessary data structure associated with the embedding-based search is often infeasible due to its high storage overhead. For example, indexing 100 GB of raw data requires 150 to 700 GB of storage, making local deployment impractical. Reducing…

The AI features in JetBrains products make me realize just how good their deterministic features were and continue to be. You get positive and actionable feedback on code rather than some strange recommendation and virtual shoulder shrug.

@… I have tried to avoid more coffee content (because it’s dangerous), but I’ll take your recommendation to check out Eckroth. 😄

Extracting Information About Publication Venues Using Citation-Informed Transformers
Brian D. Zimmerman, Joshua Folkins, Olga Vechtomova
https://arxiv.org/abs/2506.08199

Extracting Information About Publication Venues Using Citation-Informed Transformers
Scientific document embeddings contain a variety of rich features which can be harnessed for downstream tasks such as recommendation, ranking, and clustering. We explore which tangible insights can be drawn from scientific document embeddings to understand trends in computer science research featured across nine well-known venues. We collect approximately 60,000 scientific documents published between 2015 and 2023 and analyze their embeddings, which we produce with the SPECTER pre-trained langu…

»This is an awful language. Don't program in INTERCAL«
@… is talking about his work on bringing the original INTERCAL72 compiler from 1973 back to life again. Podcast recommendation, enjoy:

Advent of Computing
Welcome to Advent of Computing, the show that talks about the shocking, intriguing, and all too often relevant history of computing. A lot of little things we take for granted today have rich stories behind their creation, in each episode we will learn how older tech has lead to our modern world.

This https://arxiv.org/abs/2506.04327 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Fishing for the Optimal Roman High Latitude Time Domain Survey: Cosmological Constraints for 1,000 Possible Surveys
The upcoming Nancy Grace Roman Space Telescope is set to conduct a generation-defining SN Ia cosmology measurement with its High Latitude Time Domain Survey (HLTDS). However, between optical elements, exposure times, cadences, and survey areas, there are many survey parameters to consider. This work was part of a Roman Project Infrastructure Team effort to help the Core Community Survey (CCS) Committee finalize the HLTDS recommendation to the Roman Observations Time Allocation Committee. We sim…

lastfm_aminer: Last.fm social graph
This network contains the social graph of last.fm, a site that provides a streaming radio service, where users can search music and get personalized recommendation. A directed edge (i,j) means that user i follows user j.
This network has 136409 nodes and 1685524 edges.
Tags: Social, Online, Unweighted

Serendipitous Recommendation with Multimodal LLM
Haoting Wang, Jianling Wang, Hao Li, Fangjun Yi, Mengyu Fu, Youwei Zhang, Yifan Liu, Liang Liu, Minmin Chen, Ed H. Chi, Lichan Hong, Haokai Lu
https://arxiv.org/abs/2506.08283

Serendipitous Recommendation with Multimodal LLM
Conventional recommendation systems succeed in identifying relevant content but often fail to provide users with surprising or novel items. Multimodal Large Language Models (MLLMs) possess the world knowledge and multimodal understanding needed for serendipity, but their integration into billion-item-scale platforms presents significant challenges. In this paper, we propose a novel hierarchical framework where fine-tuned MLLMs provide high-level guidance to conventional recommendation models, s…

ich habe gerade die Petition 'Gegen Wassermangel: Bäume und Hecken auf die Äcker!' auf WeAct unterschrieben und würde mich sehr freuen, wenn weitere mitmachen
Hier könnt ihr mehr erfahren und unterzeichnen:

Gegen Wassermangel: Bäume und Hecken auf die Äcker!
💧🌳 Wassermangel, Hitzestress, Bodenerosion – unsere Äcker brauchen mehr Schatten und Wasser! Darum: Hecken und Bäume aufs Feld! Unterschreibe jetzt die WeAct-Petition für Agroforstsysteme in der Landwirtschaft. 👉 https://weact.campact.de/p/wassermangel #Agroforst #Klimaanpassung #Wasserschutz #Landwirtschaft #Petition

This https://arxiv.org/abs/2505.06612 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSI_…

Burger: Robust Graph Denoising-augmentation Fusion and Multi-semantic Modeling in Social Recommendation
In the era of rapid development of social media, social recommendation systems as hybrid recommendation systems have been widely applied. Existing methods capture interest similarity between users to filter out interest-irrelevant relations in social networks that inevitably decrease recommendation accuracy, however, limited research has a focus on the mutual influence of semantic information between the social network and the user-item interaction network for further improving social recommend…

This https://arxiv.org/abs/2501.07849 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation
Large Language Models (LLMs) have emerged as the new recommendation engines, surpassing traditional methods in both capability and scope, particularly in code generation. In this paper, we reveal a novel provider bias in LLMs: without explicit directives, these models show systematic preferences for services from specific providers in their recommendations (e.g., favoring Google Cloud over Microsoft Azure). To systematically investigate this bias, we develop an automated pipeline to construct t…

Leveraging Historical and Current Interests for Continual Sequential Recommendation
Gyuseok Lee, Hyunsik Yoo, Junyoung Hwang, SeongKu Kang, Hwanjo Yu
https://arxiv.org/abs/2506.07466

Leveraging Historical and Current Interests for Continual Sequential Recommendation
Sequential recommendation models based on the Transformer architecture show superior performance in harnessing long-range dependencies within user behavior via self-attention. However, naively updating them on continuously arriving non-stationary data streams incurs prohibitive computation costs or leads to catastrophic forgetting. To address this, we propose Continual Sequential Transformer for Recommendation (CSTRec) that effectively leverages well-preserved historical user interests while ca…

Estimation of Treatment Effects Under Nonstationarity via Truncated Difference-in-Q's
Ramesh Johari, Tianyi Peng, Wenqian Xing
https://arxiv.org/abs/2506.05308

Estimation of Treatment Effects Under Nonstationarity via Truncated Difference-in-Q's
Randomized controlled experiments (''A/B testing'') are fundamental for assessing interventions in dynamic technology-driven environments, such as recommendation systems, online marketplaces, and digital health interventions. In these systems, interventions typically impact not only the current state of the system, but also future states; therefore, accurate estimation of the global average treatment effect (or GATE) from experiments requires accounting for the dynamic temporal behavior of the …

@… I think diagramming at its best gets short shrift in this episode. The number one recommendation at the end should have been - hire a goddam information designer. There is a whole creative expert profession who have ways of designing diagrams that direct attention in the right way, that can be layered and not just additive complexes, and that are inf…

@… @… Oh, thanks! I appreciate the recommendation.

lastfm_aminer: Last.fm social graph
This network contains the social graph of last.fm, a site that provides a streaming radio service, where users can search music and get personalized recommendation. A directed edge (i,j) means that user i follows user j.
This network has 136409 nodes and 1685524 edges.
Tags: Social, Online, Unweighted

Research on E-Commerce Long-Tail Product Recommendation Mechanism Based on Large-Scale Language Models
Qingyi Lu, Haotian Lyu, Jiayun Zheng, Yang Wang, Li Zhang, Chengrui Zhou
https://arxiv.org/abs/2506.06336

Research on E-Commerce Long-Tail Product Recommendation Mechanism Based on Large-Scale Language Models
As e-commerce platforms expand their product catalogs, accurately recommending long-tail items becomes increasingly important for enhancing both user experience and platform revenue. A key challenge is the long-tail problem, where extreme data sparsity and cold-start issues limit the performance of traditional recommendation methods. To address this, we propose a novel long-tail product recommendation mechanism that integrates product text descriptions and user behavior sequences using a large-…

Macro Graph of Experts for Billion-Scale Multi-Task Recommendation
Hongyu Yao, Zijin Hong, Hao Chen, Yuanchen Bei, Zhiqing Li, Qijie Shen, Zuobin Ying, Huan Gong, Feiran Huang
https://arxiv.org/abs/2506.10520

Macro Graph of Experts for Billion-Scale Multi-Task Recommendation
Graph-based multi-task learning at billion-scale presents a significant challenge, as different tasks correspond to distinct billion-scale graphs. Traditional multi-task learning methods often neglect these graph structures, relying solely on individual user and item embeddings. However, disregarding graph structures overlooks substantial potential for improving performance. In this paper, we introduce the Macro Graph of Expert (MGOE) framework, the first approach capable of leveraging macro gr…

Contrastive Matrix Completion with Denoising and Augmented Graph Views for Robust Recommendation
Narges Nemati, Mostafa Haghir Chehreghani
https://arxiv.org/abs/2506.10658

Contrastive Matrix Completion with Denoising and Augmented Graph Views for Robust Recommendation
Matrix completion is a widely adopted framework in recommender systems, as predicting the missing entries in the user-item rating matrix enables a comprehensive understanding of user preferences. However, current graph neural network (GNN)-based approaches are highly sensitive to noisy or irrelevant edges--due to their inherent message-passing mechanisms--and are prone to overfitting, which limits their generalizability. To overcome these challenges, we propose a novel method called Matrix Comp…

Technical recommendation on multiplex MR elastography for tomographic mapping of abdominal stiffness with a focus on the pancreas and pancreatic ductal adenocarcinoma
Jakob Schattenfroh, Salma Almutawakel, Jan Bieling, Johannes Castelein, Melanie Estrella, Philippe Garteiser, Viktor Hartung, Karl H. Hillebrandt, Adrian T. Huber, Laura K\"orner, Thomas Kr\"oncke, Thomas Malinka, Hans-Jonas Meyer, Tom Meyer, Uwe Pelzer, Felix Pfister, Igor M. Sauer, Anna Speth, Bernard E. Van B…

Technical recommendation on multiplex MR elastography for tomographic mapping of abdominal stiffness with a focus on the pancreas and pancreatic ductal adenocarcinoma
Objectives: MR elastography (MRE) offers valuable mechanical tissue characterization, however, in deep abdominal organs like the pancreas conventional single-driver, single-frequency approaches often fail. This study evaluates whether multiplex MRE using multiple drivers and vibration frequencies can overcome these limitations. Methods: This study used single-shot spin-echo MRE in 18 healthy volunteers targeting the liver, pancreas, kidneys, and spleen. Each healthy volunteer underwent 16 MRE…

No Stupid Questions: An Analysis of Question Query Generation for Citation Recommendation
Brian D. Zimmerman, Julien Aubert-B\'educhaud, Florian Boudin, Akiko Aizawa, Olga Vechtomova
https://arxiv.org/abs/2506.08196

No Stupid Questions: An Analysis of Question Query Generation for Citation Recommendation
Existing techniques for citation recommendation are constrained by their adherence to article contents and metadata. We leverage GPT-4o-mini's latent expertise as an inquisitive assistant by instructing it to ask questions which, when answered, could expose new insights about an excerpt from a scientific article. We evaluate the utility of these questions as retrieval queries, measuring their effectiveness in retrieving and ranking masked target documents. In some cases, generated questions end…

Bridging the Gap Between Semantic and User Preference Spaces for Multi-modal Music Representation Learning
Xiaofeng Pan, Jing Chen, Haitong Zhang, Menglin Xing, Jiayi Wei, Xuefeng Mu, Zhongqian Xie
https://arxiv.org/abs/2505.23298

Bridging the Gap Between Semantic and User Preference Spaces for Multi-modal Music Representation Learning
Recent works of music representation learning mainly focus on learning acoustic music representations with unlabeled audios or further attempt to acquire multi-modal music representations with scarce annotated audio-text pairs. They either ignore the language semantics or rely on labeled audio datasets that are difficult and expensive to create. Moreover, merely modeling semantic space usually fails to achieve satisfactory performance on music recommendation tasks since the user preference spac…

SCIRGC: Multi-Granularity Citation Recommendation and Citation Sentence Preference Alignment
Xiangyu Li, Jingqiang Chen
https://arxiv.org/abs/2505.20103 ht…

SCIRGC: Multi-Granularity Citation Recommendation and Citation Sentence Preference Alignment
Citations are crucial in scientific research articles as they highlight the connection between the current study and prior work. However, this process is often time-consuming for researchers. In this study, we propose the SciRGC framework, which aims to automatically recommend citation articles and generate citation sentences for citation locations within articles. The framework addresses two key challenges in academic citation generation: 1) how to accurately identify the author's citation int…

Toward Understanding Bugs in Vector Database Management Systems
Yinglin Xie, Xinyi Hou, Yanjie Zhao, Shenao Wang, Kai Chen, Haoyu Wang
https://arxiv.org/abs/2506.02617

Toward Understanding Bugs in Vector Database Management Systems
Vector database management systems (VDBMSs) play a crucial role in facilitating semantic similarity searches over high-dimensional embeddings from diverse data sources. While VDBMSs are widely used in applications such as recommendation, retrieval-augmented generation (RAG), and multimodal search, their reliability remains underexplored. Traditional database reliability models cannot be directly applied to VDBMSs because of fundamental differences in data representation, query mechanisms, and s…

This https://arxiv.org/abs/2502.05206 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Safety at Scale: A Comprehensive Survey of Large Model Safety
The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a wide range of applications, including conversational AI, recommendation systems, autonomous driving, content generation, medical diagnostics, and scientific discovery. However, their widespread deployment also exposes them to significant safety risks, raisin…

UK 2025 #Publication
Severe Space Weather Impacts on UK Critical National Infrastructure
A Space weather instrumentation, measurement, modelling and risk (#SWIMMR) Project Report
Priority Recommendation CS6 : "That government and other policymakers ensure that s…

NR4DER: Neural Re-ranking for Diversified Exercise Recommendation
Xinghe Cheng, Xufang Zhou, Liangda Fang, Chaobo He, Yuyu Zhou, Weiqi Luo, Zhiguo Gong, Quanlong Guan
https://arxiv.org/abs/2506.06341

NR4DER: Neural Re-ranking for Diversified Exercise Recommendation
With the widespread adoption of online education platforms, an increasing number of students are gaining new knowledge through Massive Open Online Courses (MOOCs). Exercise recommendation have made strides toward improving student learning outcomes. However, existing methods not only struggle with high dropout rates but also fail to match the diverse learning pace of students. They frequently face difficulties in adjusting to inactive students' learning patterns and in accommodating individuali…

A friend of mine, after watching « Lucifer » on my recommendation, shared this nugget of wisdom: the Lucifer character archetype is basically Ryō Saeba from « City Hunter ». I agree.
#anime #series

Fishing for the Optimal Roman High Latitude Time Domain Survey: Cosmological Constraints for 1,000 Possible Surveys
David Rubin, Greg Aldering, Andy Fruchter, Lluis Galbany, Rebekah Hounsell, Rick Kessler, Saul Perlmutter, Ben Rose, Masao Sako, Dan Scolnic, Jannik Truong, the Roman Supernova Cosmology Project Infrastructure Team
https://

Fishing for the Optimal Roman High Latitude Time Domain Survey: Cosmological Constraints for 1,000 Possible Surveys
The upcoming Nancy Grace Roman Space Telescope is set to conduct a generation-defining SN Ia cosmology measurement with its High Latitude Time Domain Survey (HLTDS). However, between optical elements, exposure times, cadences, and survey areas, there are many survey parameters to consider. This work was part of a Roman Project Infrastructure Team effort to help the Core Community Survey (CCS) Committee finalize the HLTDS recommendation to the Roman Observations Time Allocation Committee. We sim…

Generative Next POI Recommendation with Semantic ID
Dongsheng Wang, Yuxi Huang, Shen Gao, Yifan Wang, Chengrui Huang, Shuo Shang
https://arxiv.org/abs/2506.01375

Generative Next POI Recommendation with Semantic ID
Point-of-interest (POI) recommendation systems aim to predict the next destinations of user based on their preferences and historical check-ins. Existing generative POI recommendation methods usually employ random numeric IDs for POIs, limiting the ability to model semantic relationships between similar locations. In this paper, we propose Generative Next POI Recommendation with Semantic ID (GNPR-SID), an LLM-based POI recommendation model with a novel semantic POI ID (SID) representation metho…

Survey: Graph Databases
Miguel E. Coimbra, Lucie Svit\'akov\'a, Alexandre P. Francisco, Lu\'is Veiga
https://arxiv.org/abs/2505.24758 https://

Survey: Graph Databases
Graph databases have become essential tools for managing complex and interconnected data, which is common in areas like social networks, bioinformatics, and recommendation systems. Unlike traditional relational databases, graph databases offer a more natural way to model and query intricate relationships, making them particularly effective for applications that demand flexibility and efficiency in handling interconnected data. Despite their increasing use, graph databases face notable challen…

Generating Long Semantic IDs in Parallel for Recommendation
Yupeng Hou, Jiacheng Li, Ashley Shin, Jinsung Jeon, Abhishek Santhanam, Wei Shao, Kaveh Hassani, Ning Yao, Julian McAuley
https://arxiv.org/abs/2506.05781

Generating Long Semantic IDs in Parallel for Recommendation
Semantic ID-based recommendation models tokenize each item into a small number of discrete tokens that preserve specific semantics, leading to better performance, scalability, and memory efficiency. While recent models adopt a generative approach, they often suffer from inefficient inference due to the reliance on resource-intensive beam search and multiple forward passes through the neural sequence model. As a result, the length of semantic IDs is typically restricted (e.g. to just 4 tokens), …

This https://arxiv.org/abs/2506.02916 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

MMM4Rec: An Transfer-Efficient Framework for Multi-modal Sequential Recommendation
Sequential Recommendation (SR) systems model user preferences by analyzing interaction histories. Although transferable multi-modal SR architectures demonstrate superior performance compared to traditional ID-based approaches, current methods incur substantial fine-tuning costs when adapting to new domains due to complex optimization requirements and negative transfer effects - a significant deployment bottleneck that hinders engineers from efficiently repurposing pre-trained models for novel a…

This https://arxiv.org/abs/2506.05069 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation
Driven by advances in Large Language Models (LLMs), integrating them into recommendation tasks has gained interest due to their strong semantic understanding and prompt flexibility. Prior work encoded user-item interactions or metadata into prompts for recommendations. In parallel, LLM reasoning, boosted by test-time scaling and reinforcement learning, has excelled in fields like mathematics and code, where reasoning traces and correctness signals are clear, enabling high performance and interp…

This https://arxiv.org/abs/2408.08208 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

LLM4DSR: Leveraging Large Language Model for Denoising Sequential Recommendation
Sequential Recommenders generate recommendations based on users' historical interaction sequences. However, in practice, these collected sequences are often contaminated by noisy interactions, which significantly impairs recommendation performance. Accurately identifying such noisy interactions without additional information is particularly challenging due to the absence of explicit supervisory signals indicating noise. Large Language Models (LLMs), equipped with extensive open knowledge and se…

This https://arxiv.org/abs/2505.16865 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

LARES: Latent Reasoning for Sequential Recommendation
Sequential recommender systems have become increasingly important in real-world applications that model user behavior sequences to predict their preferences. However, existing sequential recommendation methods predominantly rely on non-reasoning paradigms, which may limit the model's computational capacity and result in suboptimal recommendation performance. To address these limitations, we present LARES, a novel and scalable LAtent REasoning framework for Sequential recommendation that enhance…

This https://arxiv.org/abs/2504.04178 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommender
Large language models (LLMs), known for their comprehension capabilities and extensive knowledge, have been increasingly applied to recommendation systems (RS). Given the fundamental gap between the mechanism of LLMs and the requirement of RS, researchers have focused on fine-tuning LLMs with recommendation-specific data to enhance their performance. Language Modeling Loss (LML), originally designed for language generation tasks, is commonly adopted. However, we identify two critical limitation…

This https://arxiv.org/abs/2410.20580 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Coherence-guided Preference Disentanglement for Cross-domain Recommendations
Discovering user preferences across different domains is pivotal in cross-domain recommendation systems, particularly when platforms lack comprehensive user-item interactive data. The limited presence of shared users often hampers the effective modeling of common preferences. While leveraging shared items' attributes, such as category and popularity, can enhance cross-domain recommendation performance, the scarcity of shared items between domains has limited research in this area. To address th…

This https://arxiv.org/abs/2505.20103 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDL_…

SCIRGC: Multi-Granularity Citation Recommendation and Citation Sentence Preference Alignment
Citations are crucial in scientific research articles as they highlight the connection between the current study and prior work. However, this process is often time-consuming for researchers. In this study, we propose the SciRGC framework, which aims to automatically recommend citation articles and generate citation sentences for citation locations within articles. The framework addresses two key challenges in academic citation generation: 1) how to accurately identify the author's citation int…

Preference-based learning for news headline recommendation
Alexandre Bouras, Audrey Durand, Richard Khoury
https://arxiv.org/abs/2506.06334 https://…

Preference-based learning for news headline recommendation
This study explores strategies for optimizing news headline recommendations through preference-based learning. Using real-world data of user interactions with French-language online news posts, we learn a headline recommender agent under a contextual bandit setting. This allows us to explore the impact of translation on engagement predictions, as well as the benefits of different interactive strategies on user engagement during data collection. Our results show that explicit exploration may not…

Gated Multimodal Graph Learning for Personalized Recommendation
Sibei Liu, Yuanzhe Zhang, Xiang Li, Yunbo Liu, Chengwei Feng, Hao Yang
https://arxiv.org/abs/2506.00107

Gated Multimodal Graph Learning for Personalized Recommendation
Multimodal recommendation has emerged as a promising solution to alleviate the cold-start and sparsity problems in collaborative filtering by incorporating rich content information, such as product images and textual descriptions. However, effectively integrating heterogeneous modalities into a unified recommendation framework remains a challenge. Existing approaches often rely on fixed fusion strategies or complex architectures , which may fail to adapt to modality quality variance or introduc…

Rethinking Contrastive Learning in Session-based Recommendation
Xiaokun Zhang, Bo Xu, Fenglong Ma, Zhizheng Wang, Liang Yang, Hongfei Lin
https://arxiv.org/abs/2506.05044

Rethinking Contrastive Learning in Session-based Recommendation
Session-based recommendation aims to predict intents of anonymous users based on limited behaviors. With the ability in alleviating data sparsity, contrastive learning is prevailing in the task. However, we spot that existing contrastive learning based methods still suffer from three obstacles: (1) they overlook item-level sparsity and primarily focus on session-level sparsity; (2) they typically augment sessions using item IDs like crop, mask and reorder, failing to ensure the semantic consist…

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation
Krishna Acharya, Aleksandr V. Petrov, Juba Ziani
https://arxiv.org/abs/2506.01910

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation
We propose Generative Low-rank language model with Semantic Search (GLoSS), a generative recommendation framework that combines large language models with dense retrieval for sequential recommendation. Unlike prior methods such as GPT4Rec, which rely on lexical matching via BM25, GLoSS uses semantic search to retrieve relevant items beyond lexical matching. For query generation, we employ 4-bit quantized LlaMA-3 models fine-tuned with low-rank adaptation (LoRA), enabling efficient training and …

Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation
Keyu Zhao, Fengli Xu, Yong Li
https://arxiv.org/abs/2506.05069 ht…

Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation
Driven by advances in Large Language Models (LLMs), integrating them into recommendation tasks has gained interest due to their strong semantic understanding and prompt flexibility. Prior work encoded user-item interactions or metadata into prompts for recommendations. In parallel, LLM reasoning, boosted by test-time scaling and reinforcement learning, has excelled in fields like mathematics and code, where reasoning traces and correctness signals are clear, enabling high performance and interp…

Scaling Transformers for Discriminative Recommendation via Generative Pretraining
Chunqi Wang, Bingchao Wu, Zheng Chen, Lei Shen, Bing Wang, Xiaoyi Zeng
https://arxiv.org/abs/2506.03699

Scaling Transformers for Discriminative Recommendation via Generative Pretraining
Discriminative recommendation tasks, such as CTR (click-through rate) and CVR (conversion rate) prediction, play critical roles in the ranking stage of large-scale industrial recommender systems. However, training a discriminative model encounters a significant overfitting issue induced by data sparsity. Moreover, this overfitting issue worsens with larger models, causing them to underperform smaller ones. To address the overfitting issue and enhance model scalability, we propose a framework na…

This https://arxiv.org/abs/2409.05546 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Generative Recommender with End-to-End Learnable Item Tokenization
Generative recommendation systems have gained increasing attention as an innovative approach that directly generates item identifiers for recommendation tasks. Despite their potential, a major challenge is the effective construction of item identifiers that align well with recommender systems. Current approaches often treat item tokenization and generative recommendation training as separate processes, which can lead to suboptimal performance. To overcome this issue, we introduce ETEGRec, a nov…

Towards Human-like Preference Profiling in Sequential Recommendation
Zhongyu Ouyang, Qianlong Wen, Chunhui Zhang, Yanfang Ye, Soroush Vosoughi
https://arxiv.org/abs/2506.02261

Towards Human-like Preference Profiling in Sequential Recommendation
Sequential recommendation systems aspire to profile users by interpreting their interaction histories, echoing how humans make decisions by weighing experience, relative preference strength, and situational relevance. Yet, existing large language model (LLM)-based recommenders often fall short of mimicking the flexible, context-aware decision strategies humans exhibit, neglecting the structured, dynamic, and context-aware mechanisms fundamental to human behaviors. To bridge this gap, we propose…

MMM4Rec: An Transfer-Efficient Framework for Multi-modal Sequential Recommendation
Hao Fan, Yanrong Hu, Kai Fang, Qingyang Liu, Hongjiu Liu
https://arxiv.org/abs/2506.02916

MMM4Rec: An Transfer-Efficient Framework for Multi-modal Sequential Recommendation
Sequential Recommendation (SR) systems model user preferences by analyzing interaction histories. Although transferable multi-modal SR architectures demonstrate superior performance compared to traditional ID-based approaches, current methods incur substantial fine-tuning costs when adapting to new domains due to complex optimization requirements and negative transfer effects - a significant deployment bottleneck that hinders engineers from efficiently repurposing pre-trained models for novel a…

TransAct V2: Lifelong User Action Sequence Modeling on Pinterest Recommendation
Xue Xia, Saurabh Vishwas Joshi, Kousik Rajesh, Kangnan Li, Yangyi Lu, Nikil Pancha, Dhruvil Deven Badani, Jiajing Xu, Pong Eksombatchai
https://arxiv.org/abs/2506.02267

TransAct V2: Lifelong User Action Sequence Modeling on Pinterest Recommendation
Modeling user action sequences has become a popular focus in industrial recommendation system research, particularly for Click-Through Rate (CTR) prediction tasks. However, industry-scale CTR models often rely on short user sequences, limiting their ability to capture long-term behavior. Additionally, these models typically lack an integrated action-prediction task within a point-wise ranking framework, reducing their predictive power. They also rarely address the infrastructure challenges invo…

GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion
Sunkyung Lee, Minjin Choi, Eunseong Choi, Hye-young Kim, Jongwuk Lee
https://arxiv.org/abs/2506.01673

GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion
Generative recommendation is an emerging paradigm that leverages the extensive knowledge of large language models by formulating recommendations into a text-to-text generation task. However, existing studies face two key limitations in (i) incorporating implicit item relationships and (ii) utilizing rich yet lengthy item information. To address these challenges, we propose a Generative Recommender via semantic-Aware Multi-granular late fusion (GRAM), introducing two synergistic innovations. Fir…

SPOT-Trip: Dual-Preference Driven Out-of-Town Trip Recommendation
Yinghui Liu, Hao Miao, Guojiang Shen, Yan Zhao, Xiangjie Kong, Ivan Lee
https://arxiv.org/abs/2506.01705

SPOT-Trip: Dual-Preference Driven Out-of-Town Trip Recommendation
Out-of-town trip recommendation aims to generate a sequence of Points of Interest (POIs) for users traveling from their hometowns to previously unvisited regions based on personalized itineraries, e.g., origin, destination, and trip duration. Modeling the complex user preferences--which often exhibit a two-fold nature of static and dynamic interests--is critical for effective recommendations. However, the sparsity of out-of-town check-in data presents significant challenges in capturing such us…

Breaker: Removing Shortcut Cues with User Clustering for Single-slot Recommendation System
Chao Wang, Yue Zheng, Yujing Zhang, Yan Feng, Zhe Wang, Xiaowei Shi, An You, Yu Chen
https://arxiv.org/abs/2506.00828

Breaker: Removing Shortcut Cues with User Clustering for Single-slot Recommendation System
In a single-slot recommendation system, users are only exposed to one item at a time, and the system cannot collect user feedback on multiple items simultaneously. Therefore, only pointwise modeling solutions can be adopted, focusing solely on modeling the likelihood of clicks or conversions for items by users to learn user-item preferences, without the ability to capture the ranking information among different items directly. However, since user-side information is often much more abundant tha…

This https://arxiv.org/abs/2405.20710 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

i$^2$VAE: Interest Information Augmentation with Variational Regularizers for Cross-Domain Sequential Recommendation
Cross-Domain Sequential Recommendation (CDSR) leverages user behaviors across multiple domains to mitigate data sparsity and cold-start challenges in Single-Domain Sequential Recommendation. Existing methods primarily rely on shared users (overlapping users) to learn transferable interest representations. However, these approaches have limited information propagation, benefiting mainly overlapping users and those with rich interaction histories while neglecting non-overlapping (cold-start) and …

Replaced article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new/
[1/1]:
Causality-Inspired Fair Representation Learning for Multimodal Recommendation

Rule-Assisted Attribute Embedding
Sibo Zhao, Michael Bewong, Selasi Kwashie, Junwei Hu, Zaiwen Feng
https://arxiv.org/abs/2506.08314 https://

Rule-Assisted Attribute Embedding
Recommendation systems often overlook the rich attribute information embedded in property graphs, limiting their effectiveness. Existing graph convolutional network (GCN) models either ignore attributes or rely on simplistic triples, failing to capture deeper semantic structures. We propose RAE (Rule- Assisted Approach for Attribute Embedding), a novel method that improves recommendations by mining semantic rules from property graphs to guide attribute embedding. RAE per…

This https://arxiv.org/abs/2506.02916 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

MMM4Rec: An Transfer-Efficient Framework for Multi-modal Sequential Recommendation
Sequential Recommendation (SR) systems model user preferences by analyzing interaction histories. Although transferable multi-modal SR architectures demonstrate superior performance compared to traditional ID-based approaches, current methods incur substantial fine-tuning costs when adapting to new domains due to complex optimization requirements and negative transfer effects - a significant deployment bottleneck that hinders engineers from efficiently repurposing pre-trained models for novel a…

This https://arxiv.org/abs/2506.03437 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Quake: Adaptive Indexing for Vector Search
Vector search, the task of finding the k-nearest neighbors of high-dimensional vectors, underpins many machine learning applications, including recommendation systems and information retrieval. However, existing approximate nearest neighbor (ANN) methods perform poorly under dynamic, skewed workloads where data distributions evolve. We introduce Quake, an adaptive indexing system that maintains low latency and high recall in such environments. Quake employs a hierarchical partitioning scheme th…

This https://arxiv.org/abs/2503.23630 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Finding Interest Needle in Popularity Haystack: Improving Retrieval by Modeling Item Exposure
Recommender systems operate in closed feedback loops, where user interactions reinforce popularity bias, leading to over-recommendation of already popular items while under-exposing niche or novel content. Existing bias mitigation methods, such as Inverse Propensity Scoring (IPS) and Off-Policy Correction (OPC), primarily operate at the ranking stage or during training, lacking explicit real-time control over exposure dynamics. In this work, we introduce an exposure-aware retrieval scoring appr…

This https://arxiv.org/abs/2506.01705 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

SPOT-Trip: Dual-Preference Driven Out-of-Town Trip Recommendation
Out-of-town trip recommendation aims to generate a sequence of Points of Interest (POIs) for users traveling from their hometowns to previously unvisited regions based on personalized itineraries, e.g., origin, destination, and trip duration. Modeling the complex user preferences--which often exhibit a two-fold nature of static and dynamic interests--is critical for effective recommendations. However, the sparsity of out-of-town check-in data presents significant challenges in capturing such us…

This https://arxiv.org/abs/2412.19302 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

RecLM: Recommendation Instruction Tuning
Modern recommender systems aim to deeply understand users' complex preferences through their past interactions. While deep collaborative filtering approaches using Graph Neural Networks (GNNs) excel at capturing user-item relationships, their effectiveness is limited when handling sparse data or zero-shot scenarios, primarily due to constraints in ID-based embedding functions. To address these challenges, we propose a model-agnostic recommendation instruction-tuning paradigm that seamlessly int…

This https://arxiv.org/abs/2404.17589 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

An Offline Reinforcement Learning Algorithm Customized for Multi-Task Fusion in Large-Scale Recommender Systems
As the last critical stage of RSs, Multi-Task Fusion (MTF) is responsible for combining multiple scores outputted by Multi-Task Learning (MTL) into a final score to maximize user satisfaction, which determines the ultimate recommendation results. Recently, to optimize long-term user satisfaction within a recommendation session, Reinforcement Learning (RL) is used for MTF in the industry. However, the offline RL algorithms used for MTF so far have the following severe problems: 1) to avoid out-o…

I'm going to the #Nextcloud Summit in June! 😊 My family will join me for a weekend in #Munich. Any recommendation for a family friendly #hotel (3 girls between 5 an 10 yo)?
#münchen #followerpower

MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization
Ken Yagel, Eyal German, Aviel Ben Siman Tov
https://arxiv.org/abs/2506.07563

MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization
Personalized recommendation systems must adapt to user interactions across different domains. Traditional approaches like MLoRA apply a single adaptation per domain but lack flexibility in handling diverse user behaviors. To address this, we propose MoE-MLoRA, a mixture-of-experts framework where each expert is first trained independently to specialize in its domain before a gating network is trained to weight their contributions dynamically. We evaluate MoE-MLoRA across eight CTR models on Mov…

This https://arxiv.org/abs/2504.13703 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Consensus-aware Contrastive Learning for Group Recommendation
Group recommendation aims to provide personalized item suggestions to a group of users by reflecting their collective preferences. A fundamental challenge in this task is deriving a consensus that adequately represents the diverse interests of individual group members. Despite advancements made by deep learning-based models, existing approaches still struggle in two main areas: (1) Capturing consensus in small-group settings, which are more prevalent in real-world applications, and (2) Balancin…

Heterogeneous Sequel-Aware Graph Neural Networks for Sequential Learning
Anushka Tiwari, Haimonti Dutta, Shahrzad Khanizadeh
https://arxiv.org/abs/2506.05625

Heterogeneous Sequel-Aware Graph Neural Networks for Sequential Learning
Graph-based recommendation systems use higher-order user and item embeddings for next-item predictions. Dynamically adding collaborative signals from neighbors helps to use similar users' preferences during learning. While item-item correlations and their impact on recommendations have been studied, the efficacy of temporal item sequences for recommendations is much less explored. In this paper, we examine temporal item sequence (sequel-aware) embeddings along with higher-order user embeddings …

FACE: A Fine-grained Reference Free Evaluator for Conversational Recommender Systems
Hideaki Joko, Faegheh Hasibi
https://arxiv.org/abs/2506.00314 https://…

FACE: A Fine-grained Reference Free Evaluator for Conversational Recommender Systems
A systematic, reliable, and low-cost evaluation of Conversational Recommender Systems (CRSs) remains an open challenge. Existing automatic CRS evaluation methods are proven insufficient for evaluating the dynamic nature of recommendation conversations. This work proposes FACE: a Fine-grained, Aspect-based Conversation Evaluation method that provides evaluation scores for diverse turn and dialogue level qualities of recommendation conversations. FACE is reference-free and shows strong correlatio…

LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking
Vahid Azizi, Fatemeh Koochaki
https://arxiv.org/abs/2506.07449

LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking
Recent advances in Large Language Models (LLMs) have driven their adoption in recommender systems through Retrieval-Augmented Generation (RAG) frameworks. However, existing RAG approaches predominantly rely on flat, similarity-based retrieval that fails to leverage the rich relational structure inherent in user-item interactions. We introduce LlamaRec-LKG-RAG, a novel single-pass, end-to-end trainable framework that integrates personalized knowledge graph context into LLM-based recommendation r…

This https://arxiv.org/abs/2505.22649 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Pre-training for Recommendation Unlearning
Modern recommender systems powered by Graph Neural Networks (GNNs) excel at modeling complex user-item interactions, yet increasingly face scenarios requiring selective forgetting of training data. Beyond user requests to remove specific interactions due to privacy concerns or preference changes, regulatory frameworks mandate recommender systems' ability to eliminate the influence of certain user data from models. This recommendation unlearning challenge presents unique difficulties as removing…

This https://arxiv.org/abs/2503.09492 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Learning Cascade Ranking as One Network
Cascade Ranking is a prevalent architecture in large-scale top-k selection systems like recommendation and advertising platforms. Traditional training methods focus on single-stage optimization, neglecting interactions between stages. Recent advances have introduced interaction-aware training paradigms, but still struggle to 1) align training objectives with the goal of the entire cascade ranking (i.e., end-to-end recall of ground-truth items) and 2) learn effective collaboration patterns for d…

Quake: Adaptive Indexing for Vector Search
Jason Mohoney, Devesh Sarda, Mengze Tang, Shihabur Rahman Chowdhury, Anil Pacaci, Ihab F. Ilyas, Theodoros Rekatsinas, Shivaram Venkataraman
https://arxiv.org/abs/2506.03437

Quake: Adaptive Indexing for Vector Search
Vector search, the task of finding the k-nearest neighbors of high-dimensional vectors, underpins many machine learning applications, including recommendation systems and information retrieval. However, existing approximate nearest neighbor (ANN) methods perform poorly under dynamic, skewed workloads where data distributions evolve. We introduce Quake, an adaptive indexing system that maintains low latency and high recall in such environments. Quake employs a hierarchical partitioning scheme th…

This https://arxiv.org/abs/2505.20730 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

What LLMs Miss in Recommendations: Bridging the Gap with Retrieval-Augmented Collaborative Signals
User-item interactions contain rich collaborative signals that form the backbone of many successful recommender systems. While recent work has explored the use of large language models (LLMs) for recommendation, it remains unclear whether LLMs can effectively reason over this type of collaborative information. In this paper, we conduct a systematic comparison between LLMs and classical matrix factorization (MF) models to assess LLMs' ability to leverage user-item interaction data. We further in…

DV365: Extremely Long User History Modeling at Instagram
Wenhan Lyu, Devashish Tyagi, Yihang Yang, Ziwei Li, Ajay Somani, Karthikeyan Shanmugasundaram, Nikola Andrejevic, Ferdi Adeputra, Curtis Zeng, Arun K. Singh, Maxime Ransan, Sagar Jain
https://arxiv.org/abs/2506.00450

DV365: Extremely Long User History Modeling at Instagram
Long user history is highly valuable signal for recommendation systems, but effectively incorporating it often comes with high cost in terms of data center power consumption and GPU. In this work, we chose offline embedding over end-to-end sequence length optimization methods to enable extremely long user sequence modeling as a cost-effective solution, and propose a new user embedding learning strategy, multi-slicing and summarization, that generates highly generalizable user representation of …

Graph Contrastive Learning for Optimizing Sparse Data in Recommender Systems with LightGCL
Aravinda Jatavallabha, Prabhanjan Bharadwaj, Ashish Chander
https://arxiv.org/abs/2506.00048

Graph Contrastive Learning for Optimizing Sparse Data in Recommender Systems with LightGCL
Graph Neural Networks (GNNs) are powerful tools for recommendation systems, but they often struggle under data sparsity and noise. To address these issues, we implemented LightGCL, a graph contrastive learning model that uses Singular Value Decomposition (SVD) for robust graph augmentation, preserving semantic integrity without relying on stochastic or heuristic perturbations. LightGCL enables structural refinement and captures global collaborative signals, achieving significant gains over stat…

This https://arxiv.org/abs/2505.17549 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

EGA: A Unified End-to-End Generative Framework for Industrial Advertising Systems
Online industrial advertising system is fundamentally constrained by the inefficiency of multi-stage cascaded architectures, which filter out high-potential candidates early and fragment business decision logic across independent modules. Although recent advances in generative recommendation offer end-to-end solutions, they fall short of practical advertising requirements, lacking explicit modeling of bidding, creative selection, allocation mechanism, and payment computation that are essential …

AliBoost: Ecological Boosting Framework in Alibaba Platform
Qijie Shen, Yuanchen Bei, Zihong Huang, Jialin Zhu, Keqin Xu, Boya Du, Jiawei Tang, Yuning Jiang, Feiran Huang, Xiao Huang, Hao Chen
https://arxiv.org/abs/2506.00954

AliBoost: Ecological Boosting Framework in Alibaba Platform
Maintaining a healthy ecosystem in billion-scale online platforms is challenging, as users naturally gravitate toward popular items, leaving cold and less-explored items behind. This ''rich-get-richer'' phenomenon hinders the growth of potentially valuable cold items and harms the platform's ecosystem. Existing cold-start models primarily focus on improving initial recommendation performance for cold items but fail to address users' natural preference for popular content. In this paper, we intr…

This https://arxiv.org/abs/2503.09492 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Learning Cascade Ranking as One Network
Cascade Ranking is a prevalent architecture in large-scale top-k selection systems like recommendation and advertising platforms. Traditional training methods focus on single-stage optimization, neglecting interactions between stages. Recent advances have introduced interaction-aware training paradigms, but still struggle to 1) align training objectives with the goal of the entire cascade ranking (i.e., end-to-end recall of ground-truth items) and 2) learn effective collaboration patterns for d…

This https://arxiv.org/abs/2505.19164 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

BroadGen: A Framework for Generating Effective and Efficient Advertiser Broad Match Keyphrase Recommendations
In the domain of sponsored search advertising, the focus of Keyphrase recommendation has largely been on exact match types, which pose issues such as high management expenses, limited targeting scope, and evolving search query patterns. Alternatives like Broad match types can alleviate certain drawbacks of exact matches but present challenges like poor targeting accuracy and minimal supervisory signals owing to limited advertiser usage. This research defines the criteria for an ideal broad matc…