Summary of Fedaa: a Reinforcement Learning Perspective on Adaptive Aggregation For Fair and Robust Federated Learning, by Jialuo He et al.
FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning
by Jialuo He, Wei Chen, Xiaojin Zhang
First submitted to arxiv on: 8 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)
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 Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, FL faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. To address these issues, we introduce a novel method called FedAA, which optimizes client contributions via adaptive aggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. The proposed approach involves a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Our experiments demonstrate that FedAA outperforms state-of-the-art methods in terms of robustness while maintaining comparable levels of fairness. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated Learning is a way to train models without collecting all the data in one place. This approach helps keep personal information private. However, there are challenges with this method that make it not very good at handling different types of data or protecting against fake attacks. To solve these problems, we created a new method called FedAA. It makes sure that each device contributes to the model in a way that is safe and fair. We also used a special algorithm to help decide which devices should contribute to the model. Our tests show that FedAA does a better job at keeping the model safe from fake attacks while still being fair. |
Keywords
* Artificial intelligence * Federated learning
