Summary of Convergence Analysis Of Sequential Federated Learning on Heterogeneous Data, by Yipeng Li and Xinchen Lyu
Convergence Analysis of Sequential Federated Learning on Heterogeneous Data
by Yipeng Li, Xinchen Lyu
First submitted to arxiv on: 6 Nov 2023
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 investigates Federated Learning (FL) methods for joint training across multiple clients, focusing on sequential FL (SFL), which trains models sequentially, unlike parallel FL (PFL). The authors establish convergence guarantees for SFL on heterogeneous data, showing it outperforms PFL in certain scenarios. They demonstrate the advantages of SFL through experimental results. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper explores different methods for training machine learning models across multiple devices or clients. It looks at two main approaches: one where each device trains its own model (Parallel Federated Learning), and another where devices train their models in a specific order (Sequential Federated Learning). The researchers find that the second approach, Sequential FL, is better than the first when dealing with very different data from each client. |
Keywords
* Artificial intelligence * Federated learning * Machine learning
