Summary of Differentiable Cluster Graph Neural Network, by Yanfei Dong et al.
Differentiable Cluster Graph Neural Network
by Yanfei Dong, Mohammed Haroon Dupty, Lambert Deng, Zhuanghua Liu, Yong Liang Goh, Wee Sun Lee
First submitted to arxiv on: 25 May 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 The proposed framework addresses the limitations of Graph Neural Networks (GNNs) in processing long-range information and handling heterophilous neighborhoods. By incorporating a clustering inductive bias into the message passing mechanism, the approach uses additional cluster-nodes to capture both local and global information. The framework formulates an optimal transport-based implicit clustering objective function, which is solved through an iterative optimization process that alternates between updating cluster assignments and node-cluster-node embeddings. This approach enables end-to-end learning of the GNN and demonstrates effective performance on heterophilous and homophilous datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper develops a new framework for Graph Neural Networks to better handle long-range information propagation and heterophilous neighborhoods. The idea is to use clustering to help the network understand relationships between nodes. This is achieved by adding extra “cluster-nodes” that help the network see patterns in the data. The approach uses a special kind of optimization called optimal transport, which helps the network find the right cluster assignments. The paper shows that this approach works well on different types of datasets. |
Keywords
» Artificial intelligence » Clustering » Gnn » Objective function » Optimization
