Summary of Partial Federated Learning, by Tiantian Feng et al.
Partial Federated Learning
by Tiantian Feng, Anil Ramakrishna, Jimit Majmudar, Charith Peris, Jixuan Wang, Clement Chung, Richard Zemel, Morteza Ziyadi, Rahul Gupta
First submitted to arxiv on: 3 Mar 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 The new algorithm, Partial Federated Learning (PartialFL), proposes training machine learning models on user data constrained to edge devices while ensuring better privacy. This is achieved by allowing the egress of certain modalities or intermediate representations to the server while preventing the transmission of sensitive data like biometric signals. The authors develop a contrastive learning-based model objective that uses data labels locally, without sharing them with the cloud. The evaluation on two multi-modal datasets shows promising results for the proposed approach. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated Learning helps keep user data private by training models on devices like phones. But what if some data can be shared and others not? This problem is addressed in a new algorithm called PartialFL. It allows some data to go to the cloud, but keeps sensitive information private. The researchers tested this approach with two different types of data and found it works well. |
Keywords
* Artificial intelligence * Federated learning * Machine learning * Multi modal
