Summary of Improving Group Connectivity For Generalization Of Federated Deep Learning, by Zexi Li et al.
Improving Group Connectivity for Generalization of Federated Deep Learning
by Zexi Li, Jie Lin, Zhiqi Li, Didi Zhu, Rui Ye, Tao Shen, Tao Lin, Chao Wu
First submitted to arxiv on: 29 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 a novel approach to improve federated learning’s (FL) generalization by studying its “connectivity” from a linear mode connectivity (LMC) perspective. It leverages fixed anchor models to empirically and theoretically analyze the transitivity property of connectivity, leading to the development of FedGuCci(+), which boosts FL’s generalization under client heterogeneity across various tasks and model architectures. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning is a way for many devices to work together on a big project without sharing their individual data. The problem is that this approach doesn’t work as well as training one giant model, but still has its own benefits. This paper looks at how these separate models are connected and how we can improve the final result by better understanding this connection. The authors suggest new ways to do this, called FedGuCci(+), which helps FL work better in different situations. |
Keywords
* Artificial intelligence * Federated learning * Generalization
