Summary of Adaptive Self-supervised Robust Clustering For Unstructured Data with Unknown Cluster Number, by Chen-lu Ding et al.
Adaptive Self-supervised Robust Clustering for Unstructured Data with Unknown Cluster Number
by Chen-Lu Ding, Jiancan Wu, Wei Lin, Shiyang Shen, Xiang Wang, Yancheng Yuan
First submitted to arxiv on: 29 Jul 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 The novel Adaptive Self-supervised Robust Clustering (ASRC) approach is a deep learning-based method for unsupervised clustering of unstructured data. It learns to adaptively capture both local and global structural information using graph auto-encoders with contrastive learning, without requiring prior knowledge of the number of clusters. The method leverages robust continuous clustering to generate prototypes for negative sampling, promoting consistency among positive pairs and enlarging the gap between positive and negative samples. ASRC achieves state-of-the-art performance on seven benchmark datasets, outperforming other popular clustering models, including those that rely on prior knowledge of the number of clusters. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary ASRC is a new way to group similar things together without knowing how many groups there are beforehand. It uses special computer programs called graph auto-encoders and contrastive learning to find patterns in data that isn’t already grouped. This helps the program learn what makes different things similar or different, which can be useful for lots of applications like grouping people with similar traits or identifying objects in images. |
Keywords
» Artificial intelligence » Clustering » Deep learning » Self supervised » Unsupervised
