Summary of Incorporating Higher-order Structural Information For Graph Clustering, by Qiankun Li et al.
Incorporating Higher-order Structural Information for Graph Clustering
by Qiankun Li, Haobing Liu, Ruobing Jiang, Tingting Wang
First submitted to arxiv on: 17 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Social and Information Networks (cs.SI)
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 a novel approach to graph clustering using a graph convolutional network (GCN) that integrates both node attributes and higher-order structural information. The authors design a graph mutual infomax module to capture this structural information, which is essential for deep clustering. They also introduce a trinary self-supervised module that incorporates modularity as a structural constraint. The proposed model outperforms many state-of-the-art methods on various datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper makes it possible to group similar data points together using graphs. It uses a special kind of artificial intelligence called graph convolutional networks (GCNs) and considers not just what each point is like, but also how they are connected to each other. This helps the algorithm make better decisions about which points belong in the same group. The authors test their method on different datasets and show that it works well. |
Keywords
* Artificial intelligence * Clustering * Convolutional network * Gcn * Self supervised
