Summary of Balanced Multi-relational Graph Clustering, by Zhixiang Shen et al.
Balanced Multi-Relational Graph Clustering
by Zhixiang Shen, Haolan He, Zhao Kang
First submitted to arxiv on: 23 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); 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 The paper proposes a novel metric, Aggregation Class Distance, to quantify structural disparities among different graphs. It also introduces Balanced Multi-Relational Graph Clustering (BMGC), an approach that addresses the challenge of view imbalance in multi-relational graph clustering. BMGC combines unsupervised dominant view mining and dual signals guided representation learning to improve clustering performance. Theoretical analysis ensures the effectiveness of dominant view mining, and extensive experiments on real-world and synthetic datasets demonstrate state-of-the-art performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper tries to fix a problem in how we group things together in complex networks. Right now, there are some methods that do well at matching different groups based on what they look like. But, surprisingly, most real-world networks have an imbalance between these groups. To solve this, the authors introduce two new ideas: a way to measure how unbalanced these groups are and a new method for grouping things together that works better with imbalanced data. They test their approach on many datasets and show it performs better than existing methods. |
Keywords
» Artificial intelligence » Clustering » Representation learning » Unsupervised
