Summary of A Mutual Information Perspective on Federated Contrastive Learning, by Christos Louizos et al.
A Mutual Information Perspective on Federated Contrastive Learning
by Christos Louizos, Matthias Reisser, Denis Korzhenkov
First submitted to arxiv on: 3 May 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 The paper investigates contrastive learning in a federated setting, specifically using SimCLR and multi-view mutual information maximization. It uncovers a connection between contrastive representation learning and user verification by adding a user verification loss to each client’s local SimCLR loss, recovering a lower bound to the global multi-view mutual information. The authors extend their SimCLR variant to the federated semi-supervised setting when some labelled data are available at the clients. They also study how different sources of non-i.i.d.-ness can impact the performance of federated unsupervised learning through global mutual information maximization, finding that a global objective is beneficial for some but detrimental for others. The authors empirically evaluate their proposed extensions in various tasks to validate their claims and demonstrate generalizability to other pretraining methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper explores how computers can learn from lots of different data without seeing all the data at once. This is useful when you have lots of devices, like phones or computers, that want to work together but don’t share the same information. The researchers use a special technique called SimCLR and find a new way to make it work better. They also study what happens when some devices have more information than others, and how this affects how well the computers can learn. The results show that their approach works well in many different situations. |
Keywords
» Artificial intelligence » Pretraining » Representation learning » Semi supervised » Unsupervised
