Newest papers

Discount Yourself: Self-inclusive Freshness-weighted Gossip for Decentralised Learning under Client Outages

Qiyuan Wang, Ke Xiao, Christos Anagnostopoulos · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28545 · open-access PDF

Korean

Decentralized Federated Learning (DFL)는 중앙 서버가 아닌 이웃과 평균적인 장치에서 맞춤형 모델을 훈련시킵니다.그러나 실제 장치는 종종 몇 시간 또는 며칠 동안 오프라인으로 유지되며, 중단에서 돌아온 클라이언트는 이웃이 보유한 모델을 집계함으로써만 회복할 수 있습니다.우리는 이러한 모델 중 가장 안정적인 것이 일반적으로 클라이언트 자신의 모델이라는 것을 관찰합니다.

Machine translation (Meta M2M100); the English original follows.

Abstract

Decentralised federated learning (DFL) trains personalised models on devices that average with their neighbours rather than with a central server. Real devices, however, are often offline for hours or days, and a client returning from an outage can recover only by aggregating the models its neighbourhood holds. We observe that the stalest of these models is usually the client's own, a case that existing staleness-aware rules, which discount only the models a client receives, do not address. We formalise aggregation after an outage as estimating the state of a fully available network and derive

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange