Summary of Influence-oriented Personalized Federated Learning, by Yue Tan et al.
Influence-oriented Personalized Federated Learning
by Yue Tan, Guodong Long, Jing Jiang, Chengqi Zhang
First submitted to arxiv on: 4 Oct 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 paper proposes an innovative federated learning framework, called FedC^2I, which addresses the limitations of traditional FL methods by quantitatively measuring client-level and class-level influence. This adaptive approach enables personalized parameter aggregation for each client, realizing selective knowledge acquisition from others and personalized classifier aggregation. The proposed framework is evaluated under non-IID settings, demonstrating its superiority over existing federated learning methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper introduces a new way to improve traditional federated learning by measuring how clients influence each other. This helps clients learn more effectively when they have different types of data. The approach uses two main ideas: client-level influence and class-level influence. Client-level influence helps clients decide which information to use from others, while class-level influence helps classify data in a personalized way. The method is tested on non-IID data and performs better than other methods. |
Keywords
» Artificial intelligence » Federated learning
