Summary of Ccfc: Bridging Federated Clustering and Contrastive Learning, by Jie Yan et al.
CCFC: Bridging Federated Clustering and Contrastive Learning
by Jie Yan, Jing Liu, Zhong-Yuan Zhang
First submitted to arxiv on: 12 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 research paper proposes a new federated clustering method called cluster-contrastive federated clustering (CCFC) that enables multiple clients to collaboratively group data while keeping their data locally. Building on the success of representation learning for centralized clustering, CCFC first learns clustering-friendly representations using a tailored cluster-contrastive model. It then utilizes these representations as the foundation for its federated clustering approach. The authors demonstrate that CCFC outperforms existing baseline methods in some cases, achieving double the performance in certain scenarios. Additionally, CCFC shows superior performance in handling device failures from a practical viewpoint. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated clustering is a way to group data together without sharing it with anyone else. This research creates a new method for doing this that’s better than what we have now. They use a special kind of learning called representation learning, which helps the computer understand how things are related. By combining these two ideas, they create a method called cluster-contrastive federated clustering (CCFC). CCFC is good at grouping data together and handling situations where some devices stop working. |
Keywords
* Artificial intelligence * Clustering * Representation learning
