Summary of Federated Representation Learning in the Under-parameterized Regime, by Renpu Liu et al.
Federated Representation Learning in the Under-Parameterized Regime
by Renpu Liu, Cong Shen, Jing Yang
First submitted to arxiv on: 7 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 This paper explores federated representation learning (FRL) in the under-parameterized regime, where clients train a common representation while retaining personalized heads. The authors propose FLUTE, a novel FRL algorithm that provides provable performance guarantees for linear models. They also bridge low-rank matrix approximation techniques with FRL analysis and extend FLUTE beyond linear representations. Experimental results show FLUTE outperforms state-of-the-art FRL solutions in synthetic and real-world tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated representation learning is a way to train machines together without sharing all their data. This paper looks at how this works when the models are not over-complicated, but rather simple enough to capture important patterns. The authors created a new algorithm called FLUTE that helps these models work well even when they’re not super complex. They tested FLUTE and found it does better than other similar methods in some tasks. |
Keywords
* Artificial intelligence * Representation learning
