Summary of Federated Learning Under Partially Class-disjoint Data Via Manifold Reshaping, by Ziqing Fan et al.
Federated Learning under Partially Class-Disjoint Data via Manifold Reshaping
by Ziqing Fan, Jiangchao Yao, Ruipeng Zhang, Lingjuan Lyu, Ya Zhang, Yanfeng Wang
First submitted to arxiv on: 29 May 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 addresses the limitation of statistical heterogeneity in federated learning (FL), which can severely impact its performance. The authors propose a manifold reshaping approach called FedMR to calibrate the feature space of local training, addressing the biased optimization direction induced by partially class-disjoint data (PCDD). This is achieved by adding two interplaying losses: intra-class loss for anti-collapse and inter-class loss for proper margin among categories in the feature expansion. The authors demonstrate the effectiveness of their approach through extensive experiments on various datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this paper, researchers are trying to make a type of machine learning called federated learning work better when different devices or “clients” contribute different pieces of information. They’re proposing a new way to make sure all the information is used correctly and that the algorithm doesn’t get stuck in a bad place. This can help with things like self-driving cars, medical diagnosis, and more. |
Keywords
» Artificial intelligence » Federated learning » Machine learning » Optimization
