Summary of Fedar: Addressing Client Unavailability in Federated Learning with Local Update Approximation and Rectification, by Chutian Jiang et al.
FedAR: Addressing Client Unavailability in Federated Learning with Local Update Approximation and Rectification
by Chutian Jiang, Hansong Zhou, Xiaonan Zhang, Shayok Chakraborty
First submitted to arxiv on: 26 Jul 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 A novel federated learning approach is proposed to address the challenge of unavailable clients in collaborative model training. The Federated Approximation and Rectification (FedAR) algorithm assigns different weights to each client’s surrogate update, ensuring that both available and unavailable clients contribute to the global model. This leads to optimal convergence rates on non-IID datasets for convex and non-convex smooth loss functions. Empirical studies show that FedAR outperforms state-of-the-art FL baselines in terms of training loss, test accuracy, and bias mitigation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning is a way for many devices to work together on a machine learning project without sharing their data. One problem with this approach is that some devices might not be able to contribute at every stage. To solve this issue, researchers created an algorithm called FedAR. It makes sure all devices get involved in the project by using each device’s latest update as a substitute for its current update. The result is a high-quality global model that works well for each device. This new approach was tested and showed better results than previous methods. |
Keywords
» Artificial intelligence » Federated learning » Machine learning
