Graphs, Entities, and Step Mixture

Abstract

Existing approaches for graph neural networks commonly suffer from the oversmoothing issue, regardless of how neighborhoods are aggregated. Most methods also focus on transductive scenarios for fixed graphs, leading to poor generalization for unseen graphs. To address these issues, we propose a new graph neural network that considers both edge-based neighborhood relationships and node-based entity features, i.e. Graph Entities with Step Mixture via random walk (GESM). GESM employs a mixture of various steps through random walk to alleviate the oversmoothing problem, attention to dynamically reflect interrelations depending on node information, and structure-based regularization to enhance embedding representation. With intensive experiments, we show that the proposed GESM achieves state-of-the-art or comparable performances on eight benchmark graph datasets comprising transductive and inductive learning tasks. Furthermore, we empirically demonstrate the significance of considering global information.

5 pages, 4 figures, 3 tables accepted for ICML 2020 workshop on Graph Representation Learning and Beyond (GRL+ 2020)

References in corpus (9)

• Inductive Representation Learning on Large Graphs
• Simplifying Graph Convolutional Networks
• Pitfalls of Graph Neural Network Evaluation
• Predicting multicellular function through multi-layer tissue networks
• Attention-based Graph Neural Network for Semi-supervised Learning
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks
• NSML: Meet the MLaaS platform with a real-world case study
• NSML: A Machine Learning Platform That Enables You to Focus on Your Models
• Tripartite Heterogeneous Graph Propagation for Large-scale Social Recommendation