New research explores federated learning advancements in privacy, efficiency, and robustness · 9 sources…
ByPulseAugur Editorial·[19 sources]·
Multiple research papers published on arXiv explore advancements in federated learning, focusing on improving its efficiency, privacy, and robustness. One paper analyzes the convergence of sequential federated learning on heterogeneous data, suggesting it outperforms parallel methods. Another introduces a privacy-aligned personalized federated learning approach using compact adaptation and variable-length Gaussian communication. Further research proposes a federated random walk averaging framework to mitigate data heterogeneity and transmission errors in wireless networks, and a benchmark called FedLTLib to standardize evaluation for federated long-tail learning.
AI
IMPACT
These papers collectively advance federated learning techniques, potentially improving privacy, efficiency, and robustness in distributed AI systems.
RANK_REASON
Multiple arXiv papers detailing new research in federated learning.
arXiv:2609.19972v1 Announce Type: cross Abstract: Federated Learning (FL) is experiencing a substantial research interest, with many frameworks being developed to allow practitioners to build federations easily and quickly. Most of these efforts do not consider two main aspects t…
arXiv:2609.20501v1 Announce Type: new Abstract: Federated learning trains a shared model from private client data. In practice, data-generating distributions may differ, and the true mixture across clients is often unknown, making the underlying group distribution difficult to sp…
arXiv:2609.20174v1 Announce Type: new Abstract: We consider a federated reinforcement learning setting involving $M$ agents, all of whom interact with a common Markov Decision Process (MDP). The agents exchange information via a central server to learn the optimal value function.…
arXiv cs.LG
TIER_1English(EN)·Yasmeen Afzal, Jeremiah D. Deng, Haibo Zhang·
arXiv:2609.19559v1 Announce Type: new Abstract: Heterogeneous federated learning requires clients with diverse computational capacities to collaboratively train a global model, where each client trains a capacity-constrained submodel. Existing methods select submodel parameters u…
arXiv cs.AI
TIER_1English(EN)·Gianluca Mittone, Marco Aldinucci·
arXiv:2609.20359v1 Announce Type: cross Abstract: The symbiotic scaling of artificial intelligence models and high-performance computing systems continually creates algorithmic challenges in their convergence. Foundation models (FMs) are a crucial example, requiring months-long t…
The symbiotic scaling of artificial intelligence models and high-performance computing systems continually creates algorithmic challenges in their convergence. Foundation models (FMs) are a crucial example, requiring months-long training on thousands of cutting-edge GPUs. Sharded…
arXiv:2609.18089v1 Announce Type: new Abstract: Vehicular federated learning (VFL) enables privacy-preserving collaborative model training for intelligent transportation systems, where communication resource allocation and gradient sparsification techniques have been explored to …
arXiv cs.LG
TIER_1English(EN)·Saranraj S, Saranya M S, Alex David S, Ajay Kumar A·
arXiv:2609.16099v1 Announce Type: new Abstract: Robust aggregation methods for federated learning quietly rest on a fragile assumption: that whoever shows up in a given round is a fair sample of the full population. In practice, they rarely are. When only a handful of clients par…
arXiv:2311.03154v3 Announce Type: replace Abstract: There are two categories of methods in Federated Learning (FL) for joint training across multiple clients: (i) parallel FL (PFL), where clients train models in a parallel manner; and (ii) sequential FL (SFL), where clients train…
arXiv:2609.15625v1 Announce Type: cross Abstract: Driven by the escalating demand for privacy-preserving computing, Federated Learning (FL) has witnessed remarkable progress, becoming a cornerstone technology for bridging distributed data silos in mobile edge networks. However, i…
arXiv cs.AI
TIER_1English(EN)·Bassel Soudan, Sohail Abbas, Ahmed Kubba, Manar Wasif Abu Talib, Qassim Nasir·
arXiv:2609.15681v1 Announce Type: cross Abstract: This paper presents a systematic examination and experimental comparison of the prominent Federated Learning (FL) frameworks FedML, Flower, Substra, and OpenFL. The frameworks are evaluated experimentally by implementing Federated…
arXiv:2609.15885v1 Announce Type: cross Abstract: This study proposes a privacy-enhanced federated learning framework to address secure collaborative training in distributed data environments. The framework integrates Dynamic Differential Privacy (DDP), lightweight Homomorphic En…
arXiv cs.LG
TIER_1English(EN)·Amin Meghrazi, Srinivasan Parthasarathy, Andrew Perrault·
arXiv:2609.14591v1 Announce Type: new Abstract: Participation in federated learning (FL) comes at a cost. Clients trade off privacy, communication, and compute costs for potentially greater gains in model efficacy. This paper explores this tradeoff under the aegis of individual r…
arXiv cs.LG
TIER_1English(EN)·Doryan Lesaignoux, Enrique M\'armol Campos, Gabriele Spini, Jos\'e L. Hern\'andez-Ramos, Stephan Krenn·
arXiv:2609.15521v1 Announce Type: new Abstract: Federated learning enables multiple parties to train a shared model without centralizing raw data with the help of an aggregator, but introduces integrity risks once participants or infrastructure are not fully trustworthy. Two requ…
arXiv cs.LG
TIER_1English(EN)·Yilin Xu, Chun Hei Michael Shiu, Chih Wei Ling, Linqi Song·
arXiv:2609.15950v1 Announce Type: new Abstract: Record-level differential privacy exposes a structural misalignment in personalized federated learning when client-specific variation is low-dimensional while training repeatedly releases high-dimensional updates. In this paper, we …
arXiv:2609.14246v1 Announce Type: cross Abstract: In wireless federated learning (FL), data heterogeneity and multiple local updates induce client drift, degrading model convergence. It is further affected by unreliable wireless links, as transmission errors may invalidate model …
arXiv cs.AI
TIER_1English(EN)·Prashant Bajpai, Divya Saxena, Philippe Lalanda, German Vega·
arXiv:2609.07192v1 Announce Type: cross Abstract: Asynchronous federated learning improves scalability by updating the global model from a server-side buffer of client updates as they arrive, rather than waiting for all selected clients to finish. While efficient, this arrival-dr…
Asynchronous federated learning improves scalability by updating the global model from a server-side buffer of client updates as they arrive, rather than waiting for all selected clients to finish. While efficient, this arrival-driven aggregation can silently distort representati…
arXiv stat.ML
TIER_1English(EN)·Polycarpo Souza Neto, Jos\'e Mairton Barros da Silva J\'unior, Charles Casimiro Cavalcante·
arXiv:2609.17284v1 Announce Type: cross Abstract: Statistical heterogeneity limits federated learning when a single global classifier cannot represent client-specific label distributions. In this work, we propose Personalized Federated Knowledge Distillation with Head Adaptation …
