mlsanityData to 7 Oct 2026

On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach

arXiv 2605.26162 ↗First posted 24 May 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Asynchronous decentralized federated learning (ADFL) eliminates central coordination and global synchronization, making it attractive for large-scale and heterogeneous systems. However, frequent peer-to-peer communication, asynchronous updates on directed topologies, and non-IID data jointly lead to excessive communication overhead, biased aggregation and severe model drift. We propose PushCen-ADFL, a communication-efficient ADFL framework that enables stable training under asymmetric communication and delayed client participation. PushCen-ADFL couples communication, aggregation, and local stabilization in a shared centroid representation space, forming a closed loop between compression and optimization. Clients exchange centroid-form messages, apply average-preserving push-sum mixing to correct aggregation bias, and use a lightweight centroid regularization anchored in the same centroid space to mitigate drift under heterogeneity and staleness. A bounded, sender-deduplicated buffer further improves robustness under irregular asynchronous arrivals. Experiments on vision datasets demonstrate that PushCen-ADFL improves accuracy under data heterogeneity by up to 6% while reducing per-push communication cost by more than 80%, achieving a favorable accuracy-communication trade-off.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 45 references that are in the map. First posted on arXiv 24 May 2026.

Builds on

19 of 45 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  4. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
  5. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 188
  6. 2018Stochastic Gradient Push for Distributed Deep Learningcited by 152
  7. 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
  8. 2013Distributed optimization over time-varying directed graphscited by 77
  9. 2022DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Trainingcited by 74
  10. 2023FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Updatecited by 32
  11. 2022SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communicationcited by 21
  12. 2023Efficient and Secure Federated Learning for Financial Applicationscited by 17
7 more
  1. 2024Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guaranteescited by 10
  2. 2021Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategiescited by 9
  3. 2024SpaFL: Communication-Efficient Federated Learning with Sparse Models and Low computational Overheadcited by 9
  4. 2023A2CiD2: Accelerating Asynchronous Communication in Decentralized Deep Learningcited by 7
  5. 2024Boosting Asynchronous Decentralized Learning with Model Fragmentationcited by 6
  6. 2024DRACO: Decentralized Asynchronous Federated Learning over Row-Stochastic Wireless Networkscited by 5
  7. 2024Stragglers-Aware Low-Latency Synchronous Federated Learning via Layer-Wise Model Updatescited by 4

Built on by

Not cited yet.