Summary of Benchmarking Data Heterogeneity Evaluation Approaches For Personalized Federated Learning, by Zhilong Li et al.
Benchmarking Data Heterogeneity Evaluation Approaches for Personalized Federated Learning
by Zhilong Li, Xiaohu Wu, Xiaoli Tang, Tiantian He, Yew-Soon Ong, Mengmeng Chen, Qiqi Liu, Qicheng Lao, Han Yu
First submitted to arxiv on: 9 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 This paper addresses the need for a unified benchmark in measuring statistical heterogeneity of clients’ local datasets for personalized federated learning (PFL) models. The proposed framework includes six representative approaches and provides insights into their performance under various settings, offering guidance on selecting suitable data divergence measures for PFL systems. This is beneficial for designing PFL schemes, evaluating data heterogeneity, and addressing fairness issues in collaborative model training. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a benchmarking framework to measure statistical heterogeneity of clients’ local datasets for personalized federated learning (PFL) models. The framework includes six representative approaches and provides insights into their performance under various settings. This is helpful for designing PFL schemes, evaluating data heterogeneity, and addressing fairness issues in collaborative model training. |
Keywords
* Artificial intelligence * Federated learning
