paper-with-me

Papers

Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learning

2025-11-01 · Baris Askin, Holger R. Roth, Zhenyu Sun, Carlee Joe-Wong, Gauri Joshi, Ziyue Xu arxiv

Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its scalability is limited by synchronization overhead. Asynchronous federated learning (AFL) alleviates this issue by allowing clients to communicate independently, thereby improving wall-clock efficiency in large-scale, hardware-heterogeneous environments. However, asynchrony introduces updates computed on outdated global models (staleness) that can destabilize optimization and hinder convergence. We propose FedRevive, an AFL framework that revives stale updates through data-free knowledge distillation (DFKD). FedRevive integrates parameter-space aggregation with a lightweight, server-side DFKD process that transfers knowledge from stale client updates to the current global model without access to data. A meta-learned generator synthesizes pseudo-samples used for multi-teacher distillation. A hybrid aggregation scheme that combines raw with DFKD updates effectively mitigates staleness while retaining AFL scalability. Experiments on various vision and text benchmarks show that FedRevive achieves faster training by up to 38.4% and higher final accuracy by up to 16.5% than asynchronous baselines.

📄 PDF Abstract BibTeX arXiv:2511.00655

Code (0)

등록된 구현이 없습니다.

Tasks

Data-free Knowledge DistillationFederated Learning

Similar Papers 제목 키워드 기반

FedStale: leveraging stale client updates in federated learning

2024-05-07 · Angelo Rodio, Giovanni Neglia

Federated learning algorithms, such as FedAvg, are negatively affected by data heterogeneity and partial client participation. To mitigate the latter problem, global variance reduction methods, like FedVARP, leverage sta…

Federated Learning

Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness

2026-06-14 · Evan Duan arxiv

Activation monitors -- lightweight probes trained on a language model's internal representations -- are an increasingly common layer in deployment safety stacks. Deployed models however are rarely static: they are quanti…

FedStaleWeight: Buffered Asynchronous Federated Learning with Fair Aggregation via Staleness Reweighting

2024-06-05 · Jeffrey Ma, Alan Tu, YiLing Chen, Vijay Janapa Reddi

Federated Learning (FL) endeavors to harness decentralized data while preserving privacy, facing challenges of performance, scalability, and collaboration. Asynchronous Federated Learning (AFL) methods have emerged as pr…

FairnessFederated Learning

Tackling Intertwined Data and Device Heterogeneities in Federated Learning with Unlimited Staleness

2023-09-24 · Haoming Wang, Wei Gao

Federated Learning (FL) can be affected by data and device heterogeneities, caused by clients' different local data distributions and latencies in uploading model updates (i.e., staleness). Traditional schemes consider t…

Computational EfficiencyFederated Learning

Toward Understanding the Impact of Staleness in Distributed Machine Learning

2018-10-08 · ICLR 2019 5 · Wei Dai, Yi Zhou, Nanqing Dong, Hao Zhang 외

Many distributed machine learning (ML) systems adopt the non-synchronous execution in order to alleviate the network communication bottleneck, resulting in stale parameters that do not reflect the latest updates. Despite…

BIG-bench Machine LearningDiversity