LookHops: light multi-order convolution and pooling for graph classification

2020/12/28 by Zhangyang Gao, Haitao Lin, Gao, Zhangyang +4
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Text and Document Classification Technologies #cs.AI #cs.LG

paper · pdf · doi:10.48550/arxiv.2012.15741

9 pages, 5 figures

arxiv created 2020/12/28 · openalex publication_date 2020/12/28 · arxiv updated 2021/01/01 · openalex created_date 2021/02/15 · openalex updated_date 2026/07/28

Abstract

Convolution and pooling are the key operations to learn hierarchical representation for graph classification, where more expressive k-order(k>1) method requires more computation cost, limiting the further applications. In this paper, we investigate the strategy of selecting k via neighborhood information gain and propose light k-order convolution and pooling requiring fewer parameters while improving the performance. Comprehensive and fair experiments through six graph classification benchmarks show: 1) the performance improvement is consistent to the k-order information gain. 2) the proposed convolution requires fewer parameters while providing competitive results. 3) the proposed pooling outperforms SOTA algorithms in terms of efficiency and performance.

Citations

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Simplifying Graph Convolutional Networks
• MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
• iPool -- Information-based Pooling in Hierarchical Graph Neural Networks
• Hierarchical Graph Pooling with Structure Learning

Related

• Hybrid Low-order and Higher-order Graph Convolutional Networks
• MxPool: Multiplex Pooling for Hierarchical Graph Representation Learning
• Structural Entropy Guided Graph Hierarchical Pooling
• Clique pooling for graph classification
• Sorted Pooling in Convolutional Networks for One-shot Learning