Summary of Fedstas: Client Stratification and Client Level Sampling For Efficient Federated Learning, by Jordan Slessor et al.
FedSTaS: Client Stratification and Client Level Sampling for Efficient Federated Learning
by Jordan Slessor, Dezheng Kong, Xiaofen Tang, Zheng En Than, Linglong Kong
First submitted to arxiv on: 18 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Machine Learning (stat.ML)
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 (FL) approach, called FedSTaS, is proposed to tackle communication inefficiencies in decentralized client participation and sampling. Inspired by FedSTS and FedSampling, FedSTaS stratifies clients based on compressed gradients, optimizes the number of clients to sample using Neyman allocation, and samples local data uniformly from participating clients. Experimental results on three datasets show that FedSTaS achieves higher accuracy scores than FedSTS within a fixed number of training rounds. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning lets computers learn together without sharing private information. Some methods tried to make this process more efficient, but they didn’t solve the problem of choosing which devices should participate. This paper introduces a new way called FedSTaS that picks the right devices and takes their data in a way that preserves privacy. It works by grouping devices based on how much they’re learning, then chooses some to share information with others. The results show that this method is better than others at getting accurate answers. |
Keywords
» Artificial intelligence » Federated learning
