Hierarchical Multi-View Graph Pooling With Structure Learning

Zhen Zhang, Jiajun Bu, Martin Ester, Jianfeng Zhang, Zhao Li, Chengwei Yao, Huifen Dai, Zhi Yu, Can Wang

Abstract

Graph Neural Networks (GNNs), whch generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampling) operations, that play an important role in learning hierarchical representations, are usually overlooked. In this paper, we proposed a novel multi-view graph pooling operator dubbed as MVPool, which ranks nodes across different views with different contextual graph information. Meanwhile, attention mechanism is utilized to promote the collaboration of different views for generating robust node rankings. Then the pooling operation adaptively selects a subset of nodes to form an induced subgraph based on the ranking list. To preserve the underlying graph topological information, we further introduce a structure learning mechanism to learn a refined graph structure for the pooled graph at each layer. The proposed MVPool operator is a general strategy that can be integrated into various graph neural network architectures, including GCN, GAT and GraphSAGE, etc. By combining MVPool operator with graph neural networks, we perform hierarchical representation learning for both node and graph level classification as well as clustering tasks. Experimental results on thirteen widely used transductive and inductive benchmarks demonstrate the effectiveness of our proposed model.
BibTeX
@article{zhang2023hierarchical,
  author = {Zhen Zhang and Jiajun Bu and Martin Ester and Jianfeng Zhang and Zhao Li and Chengwei Yao and Huifen Dai and Zhi Yu and Can Wang},
  title = {{Hierarchical Multi-View Graph Pooling With Structure Learning}},
  journal = {IEEE Trans. Knowl. Data Eng.},
  year = {2023},
  doi = {10.1109/tkde.2021.3090664},
}

Loading related content...

Figure