Newest papers

The Dynamics of Collapse and Recovery in Clustered Federated Learning

Priyanka Sinha, Snigdhansu Chatterjee · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28565 · open-access PDF

Korean

클러스터 연합 학습(CFL)은 클러스터 붕괴로 고통받을 수 있습니다. 특히 불리한 초기화에서 초기 클라이언트 임무는 한 클러스터 모델에 heterogeneous 그룹을 집중시킬 수 있으며, 클러스터 모델은 배열된 타협을 향해 훈련되며, 다른 모델은 업데이트를 받지 못합니다. 현재의 모델은 클라이언트 라우팅을 결정하고, 라우팅은 후속 모델 업데이트를 결정하기 때문에, 우리는 클러스터 모델을 진화 상태로, 클라이언트 라우팅 패턴을 제어 입력으로, 그리고 라우팅 개입을 상태 dep로 제어하는 클러스터 연합 학습을 정의합니다.

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

Abstract

Clustered federated learning (CFL) can suffer from cluster collapse. In particular, under unfavorable initialization, early client assignments concentrate heterogeneous groups on one cluster model, which is then trained toward a pooled compromise, while another model receives no updates. Since the current models determine client routing and routing determines subsequent model updates, we formulate clustered federated learning as control of an unknown dynamical system, with cluster models as the evolving state, client routing patterns as the control input, and routing interventions as state dep

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28565, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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