SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism

2021/01/20 by Qingyun Sun, Jianxin Li, Sun, Qingyun +12 · 25 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Advanced Graph Neural Networks #Artificial intelligence #Bioinformatics and Genomic Networks #Computer science #Graph #Interpretability #Machine learning #Pooling #Theoretical computer science #Topic Modeling #cs.AI #cs.LG

paper · pdf · doi:10.48550/arxiv.2101.08170

published in arXiv (Cornell University) (Cornell University) · Accepted by The Web Conference (WWW) 2021

openalex publication_date 2021/01/20 · openalex created_date 2021/02/01 · arxiv created 2021/05/24 · arxiv updated 2021/05/25 · openalex updated_date 2026/08/08

Abstract

Graph representation learning has attracted increasing research attention. However, most existing studies fuse all structural features and node attributes to provide an overarching view of graphs, neglecting finer substructures' semantics, and suffering from interpretation enigmas. This paper presents a novel hierarchical subgraph-level selection and embedding based graph neural network for graph classification, namely SUGAR, to learn more discriminative subgraph representations and respond in an explanatory way. SUGAR reconstructs a sketched graph by extracting striking subgraphs as the representative part of the original graph to reveal subgraph-level patterns. To adaptively select striking subgraphs without prior knowledge, we develop a reinforcement pooling mechanism, which improves the generalization ability of the model. To differentiate subgraph representations among graphs, we present a self-supervised mutual information mechanism to encourage subgraph embedding to be mindful of the global graph structural properties by maximizing their mutual information. Extensive experiments on six typical bioinformatics datasets demonstrate a significant and consistent improvement in model quality with competitive performance and interpretability.

Cited by

• Learning and Editing Universal Graph Prompt Tuning via Reinforcement Learning
• Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift
• M-GLC: Motif-Driven Global-Local Context Graphs for Few-shot Molecular Property Prediction
• Influence Maximization in Multi-layer Social Networks Based on Differentiated Graph Embeddings
• Graph Prompting for Graph Learning Models: Recent Advances and Future Directions
• Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities
• Soft causal learning for generalized molecule property prediction: An environment perspective
• Graph Entropy Guided Node Embedding Dimension Selection for Graph Neural Networks
• A Generative Graph Contrastive Learning Model with Global Signal

Related

• Improving Subgraph Representation Learning via Multi-View Augmentation
• Self-supervised Subgraph Neural Network With Deep Reinforcement Walk Exploration
• Learning Graph Representation by Aggregating Subgraphs via Mutual Information Maximization
• Subgraph Neural Networks
• State of the Art and Potentialities of Graph-level Learning