Summary of Fair Decentralized Learning, by Sayan Biswas et al.
Fair Decentralized Learning
by Sayan Biswas, Anne-Marie Kermarrec, Rishi Sharma, Thibaud Trinca, Martijn de Vos
First submitted to arxiv on: 3 Oct 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 The proposed Decentralized Learning (DL) algorithm, Facade, tackles the issue of heterogeneous feature spaces in healthcare and other domains where nodes collaborate to train machine learning models without sharing raw data. The main challenge is to assign nodes to clusters based on their local data features without knowing which cluster they belong to beforehand. Facade dynamically assigns nodes over time and enables collaborative model training for each cluster in a decentralized manner. The paper theoretically proves the algorithm’s convergence, implements it, and compares it with three state-of-the-art baselines. Experimental results on three datasets demonstrate the superiority of Facade in terms of accuracy and fairness compared to the competitors. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Facade is an innovative approach that helps nodes in healthcare and other domains train machine learning models without sharing data. The problem is that different nodes have very different types of data, which makes it hard for them to work together. Facade solves this by grouping nodes into clusters based on their data features, so they can work together more effectively. This is important because it helps make sure that the model is fair and accurate, even when some nodes have less data than others. |
Keywords
* Artificial intelligence * Machine learning
