Summary of One Node One Model: Featuring the Missing-half For Graph Clustering, by Xuanting Xie et al.
One Node One Model: Featuring the Missing-Half for Graph Clustering
by Xuanting Xie, Bingheng Li, Erlin Pan, Zhaochen Guo, Zhao Kang, Wenyu Chen
First submitted to arxiv on: 13 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); 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 Most existing graph clustering methods primarily focus on exploiting topological structure, often neglecting the missing-half" node feature information, especially how these features can enhance clustering performance. The proposed Feature Personalized Graph Clustering (FPGC) method introduces a novel paradigm calledone node one model”, which builds an exclusive model for each node and defines the node label as a combination of predictions for node groups. FPGC identifies cluster-relevant features for each node using a squeeze-and-excitation block, integrating these features into each model to form the final representations. Additionally, the concept of feature cross is developed as a data augmentation technique to learn low-order feature interactions. The method outperforms state-of-the-art clustering methods and provides a versatile solution to enhance GNN-based models from a feature perspective. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Graph clustering helps group similar nodes together in a graph. Most existing methods focus on the connections between nodes, but ignore important information about each node itself. A new approach called FPGC tries to fix this by building a special model for each node and combining their predictions to determine which cluster it belongs to. This method is better than others at clustering graphs and can even help improve models that use graph neural networks. |
Keywords
» Artificial intelligence » Clustering » Data augmentation » Gnn
