Summary of Fedsac: Dynamic Submodel Allocation For Collaborative Fairness in Federated Learning, by Zihui Wang et al.
FedSAC: Dynamic Submodel Allocation for Collaborative Fairness in Federated Learning
by Zihui Wang, Zheng Wang, Lingjuan Lyu, Zhaopeng Peng, Zhicheng Yang, Chenglu Wen, Rongshan Yu, Cheng Wang, Xiaoliang Fan
First submitted to arxiv on: 28 May 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 The proposed framework, FedSAC, addresses the issue of collaborative fairness in federated learning by introducing a novel approach that dynamically allocates submodels to clients based on their contributions. This approach is backed by a theoretical convergence guarantee and ensures fairness by tailoring rewards to individual clients. The framework also includes a dynamic aggregation module that adaptively aggregates submodels, preserving consistency across local models and enhancing overall model accuracy. The authors demonstrate the effectiveness of FedSAC through extensive experiments on three public benchmarks, outperforming baseline methods in both fairness and model accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning is an important area of research because it allows different devices or computers to work together to learn from data without sharing their individual information. One problem with federated learning is that some devices might not get as many rewards for their contributions, which can make them less likely to participate. The proposed framework, FedSAC, tries to fix this by giving each device a “submodel” based on how much they contribute. This helps keep the devices motivated and working together well. |
Keywords
* Artificial intelligence * Federated learning
