Summary of Fedbat: Communication-efficient Federated Learning Via Learnable Binarization, by Shiwei Li and Wenchao Xu and Haozhao Wang and Xing Tang and Yining Qi and Shijie Xu and Weihong Luo and Yuhua Li and Xiuqiang He and Ruixuan Li
FedBAT: Communication-Efficient Federated Learning via Learnable Binarization
by Shiwei Li, Wenchao Xu, Haozhao Wang, Xing Tang, Yining Qi, Shijie Xu, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Li
First submitted to arxiv on: 6 Aug 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 distributed machine learning framework, Federated Binarization-Aware Training (FedBAT), is proposed to overcome the limitations of federated learning, which can be impaired by significant communication overhead. FedBAT directly learns binary model updates during local training, reducing approximation errors and improving model accuracy. The framework incorporates a novel binarization operator and designed derivatives for efficient learning, with theoretical guarantees for convergence. Experimental results on four popular datasets show that FedBAT accelerates convergence and achieves higher accuracy than baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning is a way to train models without sharing data. It’s useful when privacy matters. However, it can be slow because devices need to share their work with each other. Researchers have been trying to speed this up by making the updates smaller. A new method, called FedBAT, does this during training, not after. This makes it more accurate and faster. Tests on different datasets show that FedBAT works better than other methods. |
Keywords
» Artificial intelligence » Federated learning » Machine learning
