Summary of Federated Learning with a Single Shared Image, by Sunny Soni et al.
Federated Learning with a Single Shared Image
by Sunny Soni, Aaqib Saeed, Yuki M. Asano
First submitted to arxiv on: 18 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 The proposed method improves knowledge distillation in Federated Learning (FL) by relying only on a single shared image between clients and the server. The authors introduce an adaptive dataset pruning algorithm that selects the most informative crops generated from this single image, leading to better performance compared to using multiple individual images. The approach is extended to train heterogeneous client architectures through non-uniform distillation scheduling and client-model mirroring on the server side. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper makes it possible for different devices to work together and learn from each other without sharing private data. It’s like a team effort, where everyone contributes their own insights and knowledge to improve the overall outcome. The researchers found a way to make this process more efficient by using just one image that all participants agree on, rather than many separate images. This makes it easier for devices with different abilities and capabilities to work together. |
Keywords
» Artificial intelligence » Distillation » Federated learning » Knowledge distillation » Pruning
