Summary of Rethinking the Initialization Of Momentum in Federated Learning with Heterogeneous Data, by Chenguang Xiao and Shuo Wang
Rethinking the initialization of Momentum in Federated Learning with Heterogeneous Data
by Chenguang Xiao, Shuo Wang
First submitted to arxiv on: 29 Nov 2024
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 A novel approach to mitigating data heterogeneity in Federated Learning, titled Reversed Momentum Federated Learning (RMFL), is proposed to improve optimization techniques. By applying exponentially decayed weights to gradients, the traditional momentum cumulation is reversed, allowing for a more balanced consideration of historical and recent gradients. This innovative method is evaluated on three benchmark datasets with varying levels of heterogeneity. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this paper, researchers tackle the problem of data heterogeneity in Federated Learning by introducing Reversed Momentum Federated Learning (RMFL). The traditional momentum cumulation is revised to give more weight to historical gradients and less to recent ones. This approach helps to reduce biased local gradients during local training. The effectiveness of RMFL is tested on three benchmark datasets with different levels of heterogeneity. |
Keywords
» Artificial intelligence » Federated learning » Optimization
