Summary of Federated Learning Based on Pruning and Recovery, by Chengjie Ma
Federated Learning based on Pruning and Recovery
by Chengjie Ma
First submitted to arxiv on: 16 Mar 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 novel federated learning framework addresses the inefficiencies of traditional algorithms by integrating asynchronous learning and pruning techniques, making it suitable for realistic settings involving heterogeneous devices. The framework expedites model training while preserving accuracy through incremental restoration of model size during training. It also optimizes the server-client communication process, reducing overhead. The authors demonstrate the effectiveness of their approach through experiments on various datasets, achieving significant reductions in training time and improvements in convergence accuracy compared to conventional asynchronous FL and HeteroFL. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way to train models when devices have different internet speeds. It solves two big problems: some devices are left behind during training (staleness), and others don’t get enough data to learn well. The framework makes training faster while keeping accuracy high. It also reduces the time it takes for the server to send updates to devices, making communication more efficient. The authors tested their approach on different datasets and found that it performs better than other methods in scenarios with diverse devices and non-identical data. |
Keywords
* Artificial intelligence * Federated learning * Pruning
