Skip to content
AI News HubLIVE
Original source2 min read

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

Summary

Proposes PushCen-ADFL, a communication-efficient asynchronous decentralized federated learning framework that couples communication, aggregation, and local stabilization in a shared centroid representation space. It uses average-preserving push-sum mixing to correct aggregation bias and lightweight centroid regularization to mitigate drift under heterogeneity and staleness. Experiments on vision datasets show accuracy improvement up to 6% and communication cost reduction over 80%.

SourcearXiv Machine LearningAuthor: Jiahui Bai, Hai Dong, A. K. Qin
On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2605.26162] On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach

[Submitted on 24 May 2026]

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

View a PDF of the paper titled On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach, by Jiahui Bai and 2 other authors

View PDF HTML (experimental)

Abstract: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.

Comments: Accepted at the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026). This is the extended version with full appendix

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

ACM classes: I.2.6; I.2.11; C.2.4

Cite as: arXiv:2605.26162 [cs.LG]

(or arXiv:2605.26162v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.26162

arXiv-issued DOI via DataCite

Related DOI:

https://doi.org/10.1145/3770855.3817925

DOI(s) linking to related resources

Submission history

From: Jiahui Bai [view email] [v1] Sun, 24 May 2026 15:56:37 UTC (20,433 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach, by Jiahui Bai and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-05

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Asynchronous decentralized federated learning suffers from high communication overhead, biased aggregation, and model drift.
  • PushCen-ADFL creates a closed loop between compression and optimization via a shared centroid space.
  • Average-preserving push-sum mixing corrects bias; centroid regularization mitigates drift.
  • Achieves up to 6% accuracy gain and >80% communication cost reduction on vision datasets.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Research