Summary of Asynchronous Byzantine Federated Learning, by Bart Cox et al.
Asynchronous Byzantine Federated Learning
by Bart Cox, Abele Mălan, Lydia Y. Chen, Jérémie Decouchant
First submitted to arxiv on: 3 Jun 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 This paper presents a novel approach to federated learning (FL) that addresses the limitations of existing Byzantine fault-tolerant FL systems. Specifically, it proposes an asynchronous FL algorithm that does not require an auxiliary server dataset and is not delayed by stragglers. The proposed solution allows the server to safely update its model based on a minimum number of updates from clients, while also leveraging late client updates without compromising the integrity of the training process. The authors evaluate their approach using state-of-the-art algorithms on both image and text datasets under various attack scenarios, including gradient inversion, perturbation, and backdoor attacks. The results show that their solution trains models faster than synchronous FL solutions and maintains higher accuracy in the presence of Byzantine clients. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to learn together with computers without sharing all your data. It’s called federated learning (FL), where many devices or computers work together to train one model. Normally, this process happens at the same time for everyone, but sometimes it can be slow because some devices might be slower than others. This paper solves that problem by allowing devices to send updates to the main computer whenever they’re ready, without slowing down the whole process. They tested their idea on different types of data and found that it works better than other similar methods in many cases. |
Keywords
» Artificial intelligence » Federated learning
