Summary of Fagh: Accelerating Federated Learning with Approximated Global Hessian, by Mrinmay Sen et al.
FAGH: Accelerating Federated Learning with Approximated Global Hessian
by Mrinmay Sen, A. K. Qin, Krishna Mohan C
First submitted to arxiv on: 16 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Neural and Evolutionary Computing (cs.NE)
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 Federated learning (FL) faces a significant challenge due to the slow convergence speed of training the global model, requiring numerous communication rounds. To address this issue, we propose an FL with approximated global Hessian (FAGH) method, which leverages the first moment of the approximated global Hessian and the first moment of the global gradient to train the global model. By harnessing the approximated global Hessian curvature, FAGH accelerates the convergence of global model training, reducing the number of communication rounds and training time. Experimental results demonstrate FAGH’s effectiveness in decreasing communication rounds and training time, outperforming several state-of-the-art FL training methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In a big project called federated learning (FL), computers need to share information with each other to learn together. This process can be slow because it takes many steps for the computers to agree on what they’ve learned. To make this process faster, we created a new method that uses special math tricks to help the computers learn faster. Our method is called FL with approximated global Hessian (FAGH). It helps the computers learn faster by using clues from how fast they’re learning. We tested our method and found it works better than other methods that were trying to do the same thing. |
Keywords
* Artificial intelligence * Federated learning
