Tootfinder

Graph Parsing Networks
Yunchong Song, Siyuan Huang, Xinbing Wang, Chenghu Zhou, Zhouhan Lin
https://arxiv.org/abs/2402.14393 https://…

Graph Parsing Networks
Graph pooling compresses graph information into a compact representation. State-of-the-art graph pooling methods follow a hierarchical approach, which reduces the graph size step-by-step. These methods must balance memory efficiency with preserving node information, depending on whether they use node dropping or node clustering. Additionally, fixed pooling ratios or numbers of pooling layers are predefined for all graphs, which prevents personalized pooling structures from being captured for ea…

This https://arxiv.org/abs/2308.04666 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

Speaker Recognition Using Isomorphic Graph Attention Network Based Pooling on Self-Supervised Representation
The emergence of self-supervised representation (i.e., wav2vec 2.0) allows speaker-recognition approaches to process spoken signals through foundation models built on speech data. Nevertheless, effective fusion on the representation requires further investigating, due to the inclusion of fixed or sub-optimal temporal pooling strategies. Despite of improved strategies considering graph learning and graph attention factors, non-injective aggregation still exists in the approaches, which may influ…

🪦 CXL Is Dead In The AI Era
#ai

CXL Is Dead In The AI Era
AI Accelerator Beachfront Considerations, Memory Pooling Negatives, Custom Silicon Adoption

Optimizing Ride-Pooling Revenue: Pricing Strategies and Driver-Traveller Dynamics
Usman Akhtar, Farnoud Ghasemi, Rafal Kucharski
https://arxiv.org/abs/2403.13384

Optimizing Ride-Pooling Revenue: Pricing Strategies and Driver-Traveller Dynamics
Ride-pooling, to gain momentum, needs to be attractive for all the parties involved. This includes also drivers, who are naturally reluctant to serve pooled rides. This can be controlled by the platform's pricing strategy, which can stimulate drivers to serve pooled rides. Here, we propose an agent-based framework, where drivers serve rides that maximise their utility. We simulate a series of scenarios in Delft and compare three strategies. Our results show that drivers, when they maximize thei…

This https://arxiv.org/abs/2307.06742 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Vehicle Dispatching and Routing of On-Demand Intercity Ride-Pooling Services: A Multi-Agent Hierarchical Reinforcement Learning Approach
The integrated development of city clusters has given rise to an increasing demand for intercity travel. Intercity ride-pooling service exhibits considerable potential in upgrading traditional intercity bus services by implementing demand-responsive enhancements. Nevertheless, its online operations suffer the inherent complexities due to the coupling of vehicle resource allocation among cities and pooled-ride vehicle routing. To tackle these challenges, this study proposes a two-level framework…

Moments of Clarity: Streamlining Latent Spaces in Machine Learning using Moment Pooling
Rikab Gambhir, Athis Osathapan, Jesse Thaler
https://arxiv.org/abs/2403.08854

Moments of Clarity: Streamlining Latent Spaces in Machine Learning using Moment Pooling
Many machine learning applications involve learning a latent representation of data, which is often high-dimensional and difficult to directly interpret. In this work, we propose "Moment Pooling", a natural extension of Deep Sets networks which drastically decrease latent space dimensionality of these networks while maintaining or even improving performance. Moment Pooling generalizes the summation in Deep Sets to arbitrary multivariate moments, which enables the model to achieve a much higher …

Wait to be Faster: a Smart Pooling Framework for Dynamic Ridesharing
Xiaoyao Zhong, Jiabao Jin, Peng Cheng, Wangze Ni, Libin Zheng, Lei Chen, Xuemin Lin
https://arxiv.org/abs/2403.11099

Wait to be Faster: a Smart Pooling Framework for Dynamic Ridesharing
Ridesharing services, such as Uber or Didi, have attracted considerable attention in recent years due to their positive impact on environmental protection and the economy. Existing studies require quick responses to orders, which lack the flexibility to accommodate longer wait times for better grouping opportunities. In this paper, we address a NP-hard ridesharing problem, called Minimal Extra Time RideSharing (METRS), which balances waiting time and group quality (i.e., detour time) to improve…

Optimal design of ride-pooling as on-demand feeder services
Wenbo Fan, Weihua Gu, Meng Xu
https://arxiv.org/abs/2404.09630 https://ar…

Optimal design of ride-pooling as on-demand feeder services
The technology-enabled ride-pooling (RP) is designed as an on-demand feeder service to connect remote areas to transit terminals (or activity centers). We propose the so-called ``hold-dispatch'' operation strategy, which imposes a target number of shared rides (termed the ride-pooling size) for each vehicle to enhance RP's transportation efficiency. Analytical models are formulated at the planning level to estimate the costs of the RP operator and the patrons. Accordingly, the design problem is…

🪦 CXL Is Dead In The AI Era
#ai

CXL Is Dead In The AI Era
AI Accelerator Beachfront Considerations, Memory Pooling Negatives, Custom Silicon Adoption

Permissible Knowledge Pooling
Huimin Dong
https://arxiv.org/abs/2404.03418 https://arxiv.org/pdf/2404.03418

Permissible Knowledge Pooling
Information pooling has been extensively formalised across various logical frameworks in distributed systems, characterized by diverse information-sharing patterns. These approaches generally adopt an intersection perspective, aggregating all possible information, regardless of whether it is known or unknown to the agents. In contrast, this work adopts a unique stance, emphasising that sharing knowledge means distributing what is known, rather than what remains uncertain. This paper introduces …

The Riccati Tontine: How to Satisfy Regulators on Average
Moshe A. Milevsky, Thomas S. Salisbury
https://arxiv.org/abs/2402.14555 https://

The Riccati Tontine: How to Satisfy Regulators on Average
This paper presents a new type of modern accumulation-based tontine, called the Riccati tontine, named after two Italians: mathematician Jacobo Riccati (b. 1676, d. 1754) and financier Lorenzo di Tonti (b. 1602, d. 1684). The Riccati tontine is yet another way of pooling and sharing longevity risk, but is different from competing designs in two key ways. The first is that in the Riccati tontine, the representative investor is expected -- although not guaranteed -- to receive their money back if…

This https://arxiv.org/abs/2304.02621 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

High-fidelity Pseudo-labels for Boosting Weakly-Supervised Segmentation
Image-level weakly-supervised semantic segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. The typical approach involves training an image classification network using global average pooling (GAP) on convolutional feature maps. This enables the estimation of object locations based on class activation maps (CAMs), which identify the importance of image regions. The CAMs are then used to generate pseudo-labels, in the form of segmenta…

This https://arxiv.org/abs/2310.01225 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

A path-norm toolkit for modern networks: consequences, promises and challenges
This work introduces the first toolkit around path-norms that fully encompasses general DAG ReLU networks with biases, skip connections and any operation based on the extraction of order statistics: max pooling, GroupSort etc. This toolkit notably allows us to establish generalization bounds for modern neural networks that are not only the most widely applicable path-norm based ones, but also recover or beat the sharpest known bounds of this type. These extended path-norms further enjoy the usu…

Forecasting with panel data: Estimation uncertainty versus parameter heterogeneity
M. Hashem Pesaran, Andreas Pick, Allan Timmermann
https://arxiv.org/abs/2404.11198

Forecasting with panel data: Estimation uncertainty versus parameter heterogeneity
We provide a comprehensive examination of the predictive accuracy of panel forecasting methods based on individual, pooling, fixed effects, and Bayesian estimation, and propose optimal weights for forecast combination schemes. We consider linear panel data models, allowing for weakly exogenous regressors and correlated heterogeneity. We quantify the gains from exploiting panel data and demonstrate how forecasting performance depends on the degree of parameter heterogeneity, whether such heterog…

Dynamic U-Net: Adaptively Calibrate Features for Abdominal Multi-organ Segmentation
Jin Yang, Daniel S. Marcus, Aristeidis Sotiras
https://arxiv.org/abs/2403.07303

Dynamic U-Net: Adaptively Calibrate Features for Abdominal Multi-organ Segmentation
U-Net has been widely used for segmenting abdominal organs, achieving promising performance. However, when it is used for multi-organ segmentation, first, it may be limited in exploiting global long-range contextual information due to the implementation of standard convolutions. Second, the use of spatial-wise downsampling (e.g., max pooling or strided convolutions) in the encoding path may lead to the loss of deformable or discriminative details. Third, features upsampled from the higher level…

This https://arxiv.org/abs/2306.03218 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Optimal transport for automatic alignment of untargeted metabolomic data
Untargeted metabolomic profiling through liquid chromatography-mass spectrometry (LC-MS) measures a vast array of metabolites within biospecimens, advancing drug development, disease diagnosis, and risk prediction. However, the low throughput of LC-MS poses a major challenge for biomarker discovery, annotation, and experimental comparison, necessitating the merging of multiple datasets. Current data pooling methods encounter practical limitations due to their vulnerability to data variations an…

This https://arxiv.org/abs/2307.11133 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Contrastive Graph Pooling for Explainable Classification of Brain Networks
Functional magnetic resonance imaging (fMRI) is a commonly used technique to measure neural activation. Its application has been particularly important in identifying underlying neurodegenerative conditions such as Parkinson's, Alzheimer's, and Autism. Recent analysis of fMRI data models the brain as a graph and extracts features by graph neural networks (GNNs). However, the unique characteristics of fMRI data require a special design of GNN. Tailoring GNN to generate effective and domain-expla…

Learning of deep convolutional network image classifiers via stochastic gradient descent and over-parametrization
Michael Kohler, Adam Krzyzak, Alisha S\"anger
https://arxiv.org/abs/2404.07128

Learning of deep convolutional network image classifiers via stochastic gradient descent and over-parametrization
Image classification from independent and identically distributed random variables is considered. Image classifiers are defined which are based on a linear combination of deep convolutional networks with max-pooling layer. Here all the weights are learned by stochastic gradient descent. A general result is presented which shows that the image classifiers are able to approximate the best possible deep convolutional network. In case that the a posteriori probability satisfies a suitable hierarchi…

Simultaneous Conformal Prediction of Missing Outcomes with Propensity Score $\epsilon$-Discretization
Yonghoon Lee, Edgar Dobriban, Eric Tchetgen Tchetgen
https://arxiv.org/abs/2403.04613

Simultaneous Conformal Prediction of Missing Outcomes with Propensity Score $ε$-Discretization
We study the problem of simultaneous predictive inference on multiple outcomes missing at random. We consider a suite of possible simultaneous coverage properties, conditionally on the missingness pattern and on the -- possibly discretized/binned -- feature values. For data with discrete feature distributions, we develop a procedure which attains feature- and missingness-conditional coverage; and further improve it via pooling its results after partitioning the unobserved outcomes. To handle ge…

This https://arxiv.org/abs/2402.18162 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Out-of-Distribution Detection using Neural Activation Prior
Out-of-distribution detection is a crucial technique for deploying machine learning models in the real world to handle the unseen scenarios.In this paper, we propose a simple but effective Neural Activation Prior (NAP) for out-of-distribution detection (OOD). Our neural activation prior is based on a key observation that, for a channel before the global pooling layer of a fully trained neural network, the probability of a few of its neurons being activated with a larger response by an in-distri…

Memory Sharing with CXL: Hardware and Software Design Approaches
Sunita Jain, Nagaradhesh Yeleswarapu, Hasan Al Maruf, Rita Gupta
https://arxiv.org/abs/2404.03245

Memory Sharing with CXL: Hardware and Software Design Approaches
Compute Express Link (CXL) is a rapidly emerging coherent interconnect standard that provides opportunities for memory pooling and sharing. Memory sharing is a well-established software feature that improves memory utilization by avoiding unnecessary data movement. In this paper, we discuss multiple approaches to enable memory sharing with different generations of CXL protocol (i.e., CXL 2.0 and CXL 3.0) considering the challenges with each of the architectures from the device hardware and soft…

Synthesizing study-specific controls using generative models on open access datasets for harmonized multi-study analyses
Shruti P. Gadewar, Alyssa H. Zhu, Iyad Ba Gari, Sunanda Somu, Sophia I. Thomopoulos, Paul M. Thompson, Talia M. Nir, Neda Jahanshad
https://arxiv.org/abs/2403.00093

Synthesizing study-specific controls using generative models on open access datasets for harmonized multi-study analyses
Neuroimaging consortia can enhance reliability and generalizability of findings by pooling data across studies to achieve larger sample sizes. To adjust for site and MRI protocol effects, imaging datasets are often harmonized based on healthy controls. When data from a control group were not collected, statistical harmonization options are limited as patient characteristics and acquisition-related variables may be confounded. Here, in a multi-study neuroimaging analysis of Alzheimer's patients …

This https://arxiv.org/abs/2206.11117 has been replaced.
link: https://scholar.google.com/scholar?q=a

Causal inference in multi-cohort studies using the target trial framework to identify and minimize sources of bias
Longitudinal cohort studies, which follow a group of individuals over time, provide the opportunity to examine causal effects of complex exposures on long-term health outcomes. Utilizing data from multiple cohorts has the potential to add further benefit by improving precision of estimates through data pooling and by allowing examination of effect heterogeneity through replication of analyses across cohorts. However, the interpretation of findings can be complicated by biases that may be compou…

Spintronic Implementation of UNet for Image Segmentation
Venkatesh Vadde, Bhaskaran Muralidharan, Abhishek Sharma
https://arxiv.org/abs/2403.02863 https://…

Spintronic Implementation of UNet for Image Segmentation
Image segmentation plays a crucial role in computer vision applications like self-driving cars, satellite imagery analysis, and medical diagnosis. Implementing these complex deep neural networks on conventional hardware is highly inefficient. In this work, we propose hardware implementation of UNet for segmentation tasks, using spintronic devices. Our approach involves designing hardware for convolution, deconvolution, ReLU, and max pooling layers of the UNet architecture. We demonstrate the sy…