Summary of Da-pfl: Dynamic Affinity Aggregation For Personalized Federated Learning, by Xu Yang et al.
DA-PFL: Dynamic Affinity Aggregation for Personalized Federated Learning
by Xu Yang, Jiyuan Feng, Songyue Guo, Ye Wang, Ye Ding, Binxing Fang, Qing Liao
First submitted to arxiv on: 14 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 A novel federated learning approach, Dynamic Affinity-based Personalized Federated Learning (DA-PFL), is proposed to address the class imbalanced problem that arises when aggregating clients with similar data distributions. DA-PFL leverages an affinity metric to guide client aggregation and a dynamic strategy to reduce the risk of class imbalance in each round. Experimental results demonstrate the effectiveness of DA-PFL, achieving improved accuracy on three real-world datasets compared to state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Personalized federated learning is a new way to train models that can learn from different people’s data. The problem with this approach is that it may make things worse for some groups. This paper presents a solution called DA-PFL, which helps by finding the right balance between different groups. It works by using a special metric to decide which group should be combined and when. This makes the learning process more fair and accurate. |
Keywords
* Artificial intelligence * Federated learning
