Graph Pooling with Node Proximity for Hierarchical Representation Learning
This work addresses a bottleneck in graph neural networks for researchers and practitioners in graph data analysis, though it is incremental as it builds on existing pooling methods.
The paper tackles the problem of inefficient geometry exploitation in graph pooling by proposing a novel strategy that leverages node proximity for hierarchical representation learning, achieving state-of-the-art performance on public graph classification benchmarks.
Graph neural networks have attracted wide attentions to enable representation learning of graph data in recent works. In complement to graph convolution operators, graph pooling is crucial for extracting hierarchical representation of graph data. However, most recent graph pooling methods still fail to efficiently exploit the geometry of graph data. In this paper, we propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology. Node proximity is obtained by harmonizing the kernel representation of topology information and node features. Implicit structure-aware kernel representation of topology information allows efficient graph pooling without explicit eigendecomposition of the graph Laplacian. Similarities of node signals are adaptively evaluated with the combination of the affine transformation and kernel trick using the Gaussian RBF function. Experimental results demonstrate that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.