Summary of Lsenet: Lorentz Structural Entropy Neural Network For Deep Graph Clustering, by Li Sun et al.
LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering
by Li Sun, Zhenhao Huang, Hao Peng, Yujie Wang, Chunyang Liu, Philip S. Yu
First submitted to arxiv on: 20 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 work addresses the limitation of deep learning methods for graph clustering by introducing a fresh perspective from graph information theory. The authors formulate a differentiable structural information (DSI) in the continuous realm, which is then used to construct an optimal partitioning tree that reveals the cluster structure. This approach does not require predefined cluster numbers and is demonstrated to be superior to existing methods through extensive empirical results on real graphs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Graph clustering is a fundamental problem in machine learning that has been largely solved by deep learning methods. However, these methods still have limitations, such as requiring predefined cluster numbers. The proposed work addresses this limitation by introducing a new perspective from graph information theory and developing an approach that does not require predefined cluster numbers. The method uses differentiable structural information (DSI) to construct an optimal partitioning tree that reveals the cluster structure. |
Keywords
» Artificial intelligence » Clustering » Deep learning » Machine learning
