Tootfinder

👀 Forgejo's "Roadmap for Federation" https://codeberg.org/forgejo-contrib/federation/src/branch/main/FederationRoadmap.md — still looks like a lot of work need to be done 🥲

federation/FederationRoadmap.md at main
federation

FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attacks
Nicol\`o Romandini, Cristian Borcea, Rebecca Montanari, Luca Foschini
https://arxiv.org/abs/2508.13853

FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attacks
Federated Learning (FL) can be vulnerable to attacks, such as model poisoning, where adversaries send malicious local weights to compromise the global model. Federated Unlearning (FU) is emerging as a solution to address such vulnerabilities by selectively removing the influence of detected malicious contributors on the global model without complete retraining. However, unlike typical FU scenarios where clients are trusted and cooperative, applying FU with malicious and possibly colluding clien…

Spændende!
https://osb-alliance.de/featured/daenemark-goes-open-source

Reactive Semantics for User Interface Description Languages
Basile Pesin (Federation ENAC ISAE-SUPAERO ONERA, Universite de Toulouse, France), Celia Picard (Federation ENAC ISAE-SUPAERO ONERA, Universite de Toulouse, France), Cyril Allignol (Federation ENAC ISAE-SUPAERO ONERA, Universite de Toulouse, France)
https://arxiv.org/abs/2508.1361…

Reactive Semantics for User Interface Description Languages
User Interface Description Languages (UIDLs) are high-level languages that facilitate the development of Human-Machine Interfaces, such as Graphical User Interface (GUI) applications. They usually provide first-class primitives to specify how the program reacts to an external event (user input, network message), and how data flows through the program. Although these domain-specific languages are now widely used to implement safety-critical GUIs, little work has been invested in their formalizat…

Communication-Efficient Federated Learning with Adaptive Number of Participants
Sergey Skorik, Vladislav Dorofeev, Gleb Molodtsov, Aram Avetisyan, Dmitry Bylinkin, Daniil Medyakov, Aleksandr Beznosikov
https://arxiv.org/abs/2508.13803

Communication-Efficient Federated Learning with Adaptive Number of Participants
Rapid scaling of deep learning models has enabled performance gains across domains, yet it introduced several challenges. Federated Learning (FL) has emerged as a promising framework to address these concerns by enabling decentralized training. Nevertheless, communication efficiency remains a key bottleneck in FL, particularly under heterogeneous and dynamic client participation. Existing methods, such as FedAvg and FedProx, or other approaches, including client selection strategies, attempt to…

Personalized Subgraph Federated Learning with Sheaf Collaboration
Wenfei Liang, Yanan Zhao, Rui She, Yiming Li, Wee Peng Tay
https://arxiv.org/abs/2508.13642 https://

Personalized Subgraph Federated Learning with Sheaf Collaboration
Graph-structured data is prevalent in many applications. In subgraph federated learning (FL), this data is distributed across clients, each with a local subgraph. Personalized subgraph FL aims to develop a customized model for each client to handle diverse data distributions. However, performance variation across clients remains a key issue due to the heterogeneity of local subgraphs. To overcome the challenge, we propose FedSheafHN, a novel framework built on a sheaf collaboration mechanism to…

Trans-XFed: An Explainable Federated Learning for Supply Chain Credit Assessment
Jie Shi, Arno P. J. M. Siebes, Siamak Mehrkanoon
https://arxiv.org/abs/2508.13715 https://

Trans-XFed: An Explainable Federated Learning for Supply Chain Credit Assessment
This paper proposes a Trans-XFed architecture that combines federated learning with explainable AI techniques for supply chain credit assessment. The proposed model aims to address several key challenges, including privacy, information silos, class imbalance, non-identically and independently distributed (Non-IID) data, and model interpretability in supply chain credit assessment. We introduce a performance-based client selection strategy (PBCS) to tackle class imbalance and Non-IID problems. T…

Who to Trust? Aggregating Client Knowledge in Logit-Based Federated Learning
Viktor Kovalchuk, Nikita Kotelevskii, Maxim Panov, Samuel Horv\'ath, Martin Tak\'a\v{c}
https://arxiv.org/abs/2509.15147

Who to Trust? Aggregating Client Knowledge in Logit-Based Federated Learning
Federated learning (FL) usually shares model weights or gradients, which is costly for large models. Logit-based FL reduces this cost by sharing only logits computed on a public proxy dataset. However, aggregating information from heterogeneous clients is still challenging. This paper studies this problem, introduces and compares three logit aggregation methods: simple averaging, uncertainty-weighted averaging, and a learned meta-aggregator. Evaluated on MNIST and CIFAR-10, these methods reduce…

Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning
Lei Wang, Jieming Bian, Letian Zhang, Jie Xu
https://arxiv.org/abs/2509.15087 https://

Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning
Large Language Models (LLMs) have demonstrated impressive capabilities across various tasks, but fine-tuning them for domain-specific applications often requires substantial domain-specific data that may be distributed across multiple organizations. Federated Learning (FL) offers a privacy-preserving solution, but faces challenges with computational constraints when applied to LLMs. Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient fine-tuning approach, though a single LoRA module…

Towards a Larger Model via One-Shot Federated Learning on Heterogeneous Client Models
Wenxuan Ye, Xueli An, Onur Ayan, Junfan Wang, Xueqiang Yan, Georg Carle
https://arxiv.org/abs/2508.13625

Towards a Larger Model via One-Shot Federated Learning on Heterogeneous Client Models
Large models, renowned for superior performance, outperform smaller ones even without billion-parameter scales. While mobile network servers have ample computational resources to support larger models than client devices, privacy constraints prevent clients from directly sharing their raw data. Federated Learning (FL) enables decentralized clients to collaboratively train a shared model by exchanging model parameters instead of transmitting raw data. Yet, it requires a uniform model architectur…