Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering
24. července 2023
O prezentaci
Graph neural networks (GNNs) based methods have achieved impressive performance on node clustering task. However, they are designed on the homophilic assumption of graph and clustering on heterophilic graph is overlooked. Due to the lack of labels, it is impossible to first identify a graph as homophilic or heterophilic before a suitable GNN model can be found. Hence, clustering on real-world graph with various levels of homophily poses a new challenge to the graph research community. To fill this gap, we propose a novel graph clustering method, which contains three key components: graph reconstruction, a mixed filter, and dual graph clustering network. To be graph-agnostic, we empirically construct two graphs which are high homophily and heterophily from each data. The mixed filter based on the new graphs extracts both low-frequency and high-frequency information. To reduce the adverse coupling between node attribute and topological structure, we separately map them into two subspaces in dual graph clustering network. Extensive experiments on 11 benchmark graphs demonstrate our promising performance. In particular, our method dominates others on heterophilic graphs.Graph neural networks (GNNs) based methods have achieved impressive performance on node clustering task. However, they are designed on the homophilic assumption of graph and clustering on heterophilic graph is overlooked. Due to the lack of labels, it is impossible to first identify a graph as homophilic or heterophilic before a suitable GNN model can be found. Hence, clustering on real-world graph with various levels of homophily poses a new challenge to the graph research community. To fill th…
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Raising the Cost of Malicious AI-Powered Image Editing
Zhlédnout později
Hadi Salman, …
Confidence and Dispersity Speak: Characterizing Prediction Matrix for Unsupervised Accuracy Estimation
Zhlédnout později
Weijian Deng, …
Robust Consensus in Ranking Data Analysis: Definitions, Properties and Computational Issues
Zhlédnout později
Opening remarks
Zhlédnout později
Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond
Zhlédnout později
Jaeyoung Cha, …
