Summary of Revisiting Modularity Maximization For Graph Clustering: a Contrastive Learning Perspective, by Yunfei Liu et al.
Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspective
by Yunfei Liu, Jintang Li, Yuehe Chen, Ruofan Wu, Ericbk Wang, Jing Zhou, Sheng Tian, Shuheng Shen, Xing Fu, Changhua Meng, Weiqiang Wang, Liang Chen
First submitted to arxiv on: 20 Jun 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 In this paper, researchers delve into the mechanisms underlying modularity maximization, a popular approach for community detection in graphs. They explore the connections between modularity maximization and graph contrastive learning, which has emerged as a dominant line of research in graph clustering. The authors propose MAGI, a community-aware graph clustering framework that leverages modularity maximization as a contrastive pretext task to uncover community information in graphs while avoiding semantic drift. MAGI is shown to be effective and scalable on multiple graph datasets, outperforming state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Graphs are like networks of friends. Imagine you’re trying to group your friends into teams based on who they hang out with. That’s kind of what this paper is about: grouping nodes in a graph together based on how connected they are. There are lots of ways to do this, but some methods are better than others. This paper looks at one method called modularity maximization and figures out why it works so well. The authors even come up with a new way to use modularity maximization that makes it faster and more accurate. |
Keywords
» Artificial intelligence » Clustering
