Skip to content

FedRAW: Preserving Rare-Label Influence in Asynchronous Federated Learning

Sep 2026 · arXiv.org · Vol abs/2609.07192 · 0 citations · 21 references
Computer Science

TL;DR

FedRAW is proposed, a fully server-side aggregation method that preserves rare-label influence without changing local training, client objectives, or communication protocols, and improves rarelabel accuracy while preserving comparable global accuracy and adding negligible server-side computation.

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-driven aggregation can silently distort representation learning under heterogeneous participation. We identify silent rarity failure, a hidden failure mode in which clients holding rare labels contribute too weakly to the global model even though its overall accuracy appears largely unaffected. This failure arises from two coupled effects: rare-label clients may submit updates less frequently when they are slower or less available, creating participation bias; and once their updates enter the buffer, standard asynchronous aggregation assigns them no compensating influence, creating aggregation bias. We propose FedRAW, a fully server-side aggregation method that preserves rare-label influence without changing local training, client objectives, or communication protocols. FedRAW combines client-level update deduplication, which prevents frequently arriving clients from repeatedly dominating the update buffer, with rare-label-aware weighting, which increases the influence of clients carrying low-coverage labels. We formalize silent rarity failure through participation and aggregation bias, and show that FedRAW increases rare-label client influence over uniform aggregation while preserving convergence. Across EMNIST Balanced, CIFAR-10, HAM10000, and ISIC-2019, FedRAW improves rarelabel accuracy while preserving comparable global accuracy and adding negligible server-side computation.

View source

Similar papers

Book Open access Nov 2026

Correlation-Guided Latent Sharing for Non-IID Federated Learning

Correlation-Guided Latent Sharing is proposed, a federated learning framework that selectively augments client training using latent information received from statistically aligned peers and improves accuracy and macro-F1 over FedAvg and FedProx, with the largest gains appearing in the strongest heterogeneity settings.

Mahran Jazi, Sharva Gogawale, I. Ben-gal · 0 citations
#federated learning Book Open access Nov 2026

FedHCA: Hierarchical Contribution-Aware Aggregation for Asynchronous Federated Class-Incremental Learning

Federated class-incremental learning (FCIL) aims to learn emerging classes across decentralized clients while preserving previously acquired knowledge. Existing FCIL methods are often designed or evaluated under relatively synchronous new-class exposure settings, while in realistic federated systems, a new class may in...

Yan Duan, Xin Qin, Xiaodong Yang et al. · 0 citations

FedLTLib: A Comprehensive Benchmark for Federated Long-Tail Learning

FedLTLib, a comprehensive benchmark tailored for FL-LT, establishes a standardized evaluation framework and can perform fair and reproducible evaluations of algorithm robustness and generalization capabilities under a unified experimental protocol, ultimately advancing the deployment of robust intelligence in mobile co...

Chang-Kun Lin, Jun-Xiao Wang · 0 citations
#artificial intelligence Preprint Oct 2026

CoASFL: Coupled Consistency Optimization for Asynchronous Split Federated Learning

CoASFL is proposed, an inconsistency-aware asynchronous SFL framework that incorporates a dynamic activation merging mechanism and a consistency-aware model aggregation mechanism that effectively suppresses inconsistency propagation during asynchronous training.

Jun-Hao Cheng, Yun-Ming Liao, Hong-Li Xu et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Sep 29, 2026

Who we become when we talk to machines

Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.