Summary of Federated One-shot Ensemble Clustering, by Rui Duan et al.
Federated One-Shot Ensemble Clustering
by Rui Duan, Xin Xiong, Jueyi Liu, Katherine P. Liao, Tianxi Cai
First submitted to arxiv on: 12 Sep 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Machine Learning (cs.LG); Applications (stat.AP)
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 proposes Federated One-shot Ensemble Clustering (FONT), an algorithm designed to facilitate cluster analysis across multiple institutions while respecting data-sharing restrictions. FONT enables sites to share only fitted model parameters and class labels, ensuring privacy and minimizing communication overhead. By combining locally fitted models into a data-adaptive ensemble, the algorithm is robust to differences in cluster proportions and applicable to various clustering techniques. Simulation studies demonstrate its superior performance compared to existing benchmark methods. FONT’s effectiveness is validated through theoretical analysis, which highlights the importance of learning data-adaptive weights. The paper also presents a real-world application, using FONT to identify subgroups of patients with rheumatoid arthritis across two health systems. The results show improved consistency of patient clusters across sites and highlight the limitations of locally fitted clusters. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary FONT is a new algorithm that helps institutions share information about groups of people without sharing their personal details. It’s useful when many different places want to work together, but they have strict rules about sharing data. FONT makes sure that each place only shares what it needs to, while still getting accurate results. It works well with different types of groupings and is good at finding patterns that are the same across different groups. FONT was tested on a real problem – identifying patient groups in two health systems. The results show that FONT is better than other methods at finding consistent groups, even when each place has its own way of grouping people. |
Keywords
» Artificial intelligence » Clustering » One shot
