Summary of Mixture Of Multilayer Stochastic Block Models For Multiview Clustering, by Kylliann De Santiago et al.
Mixture of multilayer stochastic block models for multiview clustering
by Kylliann De Santiago, Marie Szafranski, Christophe Ambroise
First submitted to arxiv on: 9 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Statistics Theory (math.ST); Machine Learning (stat.ML)
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 proposed method aggregates multiple clustering results from different sources by encoding each partition as a co-membership matrix between observations. A mixture of multilayer Stochastic Block Models (SBM) groups similar co-membership matrices into components and partitions observations into clusters based on their specificities within the components. The model parameters are identified, and a variational Bayesian EM algorithm is developed for estimation. The Bayesian framework allows for selecting an optimal number of clusters and components. The method is compared to consensus clustering and tensor-based algorithms using synthetic data and applied to analyze global food trading networks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research proposes a new way to combine different clusterings from various sources. Imagine you have many groups, each with its own set of people or things. Each group has its own rules for who belongs and who doesn’t. The method takes these groups and combines them into larger categories based on what they have in common. This helps find patterns and relationships between the groups that might not be apparent otherwise. The researchers tested their approach using made-up data and real-world examples, like studying global food trading networks. |
Keywords
* Artificial intelligence * Clustering * Synthetic data
