Summary of Fedp3: Federated Personalized and Privacy-friendly Network Pruning Under Model Heterogeneity, by Kai Yi et al.
FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
by Kai Yi, Nidham Gazagnadou, Peter Richtárik, Lingjuan Lyu
First submitted to arxiv on: 15 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR)
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 paper proposes an adaptable federated learning framework called FedP3 (Federated Personalized and Privacy-friendly network Pruning) to address the challenge of client-side model heterogeneity in federated learning. This issue arises when clients have varying memory storage, processing capabilities, and network bandwidth, making it essential to customize a unique model for each client. The authors present an effective methodology that incorporates well-established techniques and offer theoretical interpretations and validations of FedP3 and its locally differential-private variant, DP-FedP3. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about a new way to train AI models using private information from many devices while keeping the data safe. This is important because it helps protect people’s privacy. The problem is that each device has different hardware and software, which makes it hard to create one model that works for all of them. The authors came up with a solution called FedP3, which is special because it can adapt to each device’s unique situation. |
Keywords
» Artificial intelligence » Federated learning » Pruning
