English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Federated learning (FL) stands as a paradigmatic approach that facilitatesmodel training across heterogeneous and diverse datasets originating fromvarious data providers. However, conventional FLs fall short of achievingconsistent performance, potentially leading to performance degradation forclients who are disadvantaged in data resources. Influenced by the Mattheweffect, deploying a performance-imbalanced global model in applications furtherimpedes the generation of high-quality data from disadvantaged clients,exacerbating the disparities in data resources among clients. In this work, wepropose anti-Matthew fairness for the global model at the client level,requiring equal accuracy and equal decision bias across clients. To balance thetrade-off between achieving anti-Matthew fairness and performance optimality,we formalize the anti-Matthew effect federated learning (anti-Matthew FL) as amulti-constrained multi-objectives optimization (MCMOO) problem and propose athree-stage multi-gradient descent algorithm to obtain the Pareto optimality.We theoretically analyze the convergence and time complexity of our proposedalgorithms. Additionally, through extensive experimentation, we demonstratethat our proposed anti-Matthew FL outperforms other state-of-the-art FLalgorithms in achieving a high-performance global model while effectivelybridging performance gaps among clients. We hope this work provides valuableinsights into the manifestation of the Matthew effect in FL and otherdecentralized learning scenarios and can contribute to designing fairerlearning mechanisms, ultimately fostering societal welfare.

Anti-Matthew FL: Bridging the Performance Gap in Federated Learning to Counteract the Matthew Effect