Summary of Fedmaba: Towards Fair Federated Learning Through Multi-armed Bandits Allocation, by Zhichao Wang et al.
FedMABA: Towards Fair Federated Learning through Multi-Armed Bandits Allocation
by Zhichao Wang, Lin Wang, Yongxin Guo, Ying-Jun Angela Zhang, Xiaoying Tang
First submitted to arxiv on: 26 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a solution to address the issue of inconsistent performance in federated learning (FL) due to statistical heterogeneity among clients. FL is a collaborative approach that enables model training on decentralized data while preserving client privacy. However, server models may favor certain clients, leading to poor performance for others, compromising fairness. To mitigate this issue, the authors introduce an adversarial multi-armed bandit approach, optimizing the proposed objective with constraints on performance disparities. The novel algorithm, FedMABA, is designed to allocate tasks among diverse clients with different data distributions, enhancing fairness. Experimental results in various non-IID scenarios demonstrate the effectiveness of FedMABA in achieving fairness. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning (FL) helps many devices learn together without sharing personal data. However, this approach can be unfair because some devices might get better or worse results than others. The authors propose a new method to make FL more fair by using an algorithm that balances the performance of different devices. They test their method in various scenarios and show that it works well. |
Keywords
» Artificial intelligence » Federated learning
