On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911717746802688 |
|---|---|
| author | Bai, Jiahui Dong, Hai Qin, A. K. |
| author_facet | Bai, Jiahui Dong, Hai Qin, A. K. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_26162 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach Bai, Jiahui Dong, Hai Qin, A. K. Machine Learning Artificial Intelligence I.2.6; I.2.11; C.2.4 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. |
| title | On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach |
| topic | Machine Learning Artificial Intelligence I.2.6; I.2.11; C.2.4 |
| url | https://arxiv.org/abs/2605.26162 |