Geom-GCN: Geometric Graph Convolutional Networks

Abstract

Message-passing neural networks (MPNNs) have been successfully applied to representation learning on graphs in a variety of real-world applications. However, two fundamental weaknesses of MPNNs' aggregators limit their ability to represent graph-structured data: losing the structural information of nodes in neighborhoods and lacking the ability to capture long-range dependencies in disassortative graphs. Few studies have noticed the weaknesses from different perspectives. From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses. The behind basic idea is the aggregation on a graph can benefit from a continuous space underlying the graph. The proposed aggregation scheme is permutation-invariant and consists of three modules, node embedding, structural neighborhood, and bi-level aggregation. We also present an implementation of the scheme in graph convolutional networks, termed Geom-GCN (Geometric Graph Convolutional Networks), to perform transductive learning on graphs. Experimental results show the proposed Geom-GCN achieved state-of-the-art performance on a wide range of open datasets of graphs. Code is available at https://github.com/graphdml-uiuc-jlu/geom-gcn.

Published as a conference paper at ICLR 2020

References in corpus (2)

• Simplifying Graph Convolutional Networks
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling

Cited by in corpus (23)

• Towards Deeper Graph Neural Networks
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• Search to aggregate neighborhood for graph neural network
• PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations
• Improving Graph Neural Networks with Simple Architecture Design
• Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs
• GCN-SL: Graph Convolutional Networks with Structure Learning for Graphs under Heterophily
• GMLP: Building Scalable and Flexible Graph Neural Networks with Feature-Message Passing
• A Hyperbolic-to-Hyperbolic Graph Convolutional Network
• Price graphs: Utilizing the structural information of financial time series for stock prediction
• Tree Decomposed Graph Neural Network
• Permutohedral-GCN: Graph Convolutional Networks with Global Attention
• CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks
• Search For Deep Graph Neural Networks
• Hyperbolic Neural Collaborative Recommender
• SoGCN: Second-Order Graph Convolutional Networks
• Local Algorithms for Finding Densely Connected Clusters
• Label-informed Graph Structure Learning for Node Classification
• FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping
• A Survey on Role-Oriented Network Embedding
• Towards a Taxonomy of Graph Learning Datasets
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast
• Statistical Estimation from Dependent Data