Summary of Self Supervised Correlation-based Permutations For Multi-view Clustering, by Ran Eisenberg et al.
Self Supervised Correlation-based Permutations for Multi-View Clustering
by Ran Eisenberg, Jonathan Svirsky, Ofir Lindenbaum
First submitted to arxiv on: 26 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 deep learning-based multi-view clustering framework fuses information from different modalities to enhance data analysis tasks, including clustering. The approach learns meaningful fused data representations using a novel permutation-based canonical correlation objective and identifies consistent pseudo-labels across multiple views for cluster assignments. This end-to-end method is demonstrated on ten MVC benchmark datasets, showing its effectiveness in approximating supervised linear discrimination analysis (LDA) representation. Additionally, an error bound induced by false-pseudo label annotations is provided. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to group similar data points together from different sources, like images and numbers. They create a special kind of computer program that can look at multiple types of data at the same time and find patterns that make sense. This helps with grouping similar things together, which is useful for lots of tasks like image recognition or analyzing customer information. The authors test their idea on many different datasets and show it works well. |
Keywords
* Artificial intelligence * Clustering * Deep learning * Supervised
