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 (7)

• Assortative mixing in networks
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• Simplifying Graph Convolutional Networks
• struc2vec: Learning Node Representations from Structural Identity
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Machine learning meets network science: dimensionality reduction for fast and efficient embedding of networks in the hyperbolic space

Cited by in corpus (73)

• Towards Deeper Graph Neural Networks
• Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
• Graph Neural Networks: Taxonomy, Advances and Trends
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• Graph Information Bottleneck
• Adaptive Universal Generalized PageRank Graph Neural Network
• Is Homophily a Necessity for Graph Neural Networks?
• Implicit Graph Neural Networks
• MagNet: A Neural Network for Directed Graphs
• Understanding over-squashing and bottlenecks on graphs via curvature
• BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
• Bag of Tricks for Node Classification with Graph Neural Networks
• Non-Local Graph Neural Networks
• Search to aggregate neighborhood for graph neural network
• New Benchmarks for Learning on Non-Homophilous Graphs
• Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs
• Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks
• Optimal Transport Graph Neural Networks
• Automated Self-Supervised Learning for Graphs
• Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks
• Local Augmentation for Graph Neural Networks
• PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations
• Improving Graph Neural Networks with Simple Architecture Design
• SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection
• Graph Neural Networks Inspired by Classical Iterative Algorithms
• Neural Link Prediction with Walk Pooling
• Node Injection Attack Based on Label Propagation Against Graph Neural Network
• Geometric Scattering Attention Networks
• Global Attention Improves Graph Networks Generalization
• Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods
• Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery
• Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
• The Impact of Global Structural Information in Graph Neural Networks Applications
• R-GSN: The Relation-based Graph Similar Network for Heterogeneous Graph
• Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
• Deepened Graph Auto-Encoders Help Stabilize and Enhance Link Prediction
• Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs
• An Overview on the Application of Graph Neural Networks in Wireless Networks
• GMLP: Building Scalable and Flexible Graph Neural Networks with Feature-Message Passing
• A Hyperbolic-to-Hyperbolic Graph Convolutional Network
• GCN-SL: Graph Convolutional Networks with Structure Learning for Graphs under Heterophily
• Price graphs: Utilizing the structural information of financial time series for stock prediction
• Label-Wise Graph Convolutional Network for Heterophilic Graphs
• Quaternion Graph Neural Networks
• Tree Decomposed Graph Neural Network
• $p$-Laplacian Based Graph Neural Networks
• Permutohedral-GCN: Graph Convolutional Networks with Global Attention
• Learning to Evolve on Dynamic Graphs
• Learnable Structural Semantic Readout for Graph Classification
• Hyperbolic Neural Collaborative Recommender
• CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks
• Search For Deep Graph Neural Networks
• A Biased Graph Neural Network Sampler with Near-Optimal Regret
• Graph Neural Networks with Feature and Structure Aware Random Walk
• SoGCN: Second-Order Graph Convolutional Networks
• Graph Attention Networks with Positional Embeddings
• From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation
• BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks
• AKE-GNN: Effective Graph Learning with Adaptive Knowledge Exchange
• Learning Parametrised Graph Shift Operators
• Local Algorithms for Finding Densely Connected Clusters
• A Survey on Role-Oriented Network Embedding
• RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks
• Implicit vs Unfolded Graph Neural Networks
• On the Global Self-attention Mechanism for Graph Convolutional Networks
• Graph Feature Gating Networks
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast
• A Block-based Generative Model for Attributed Networks Embedding
• Statistical Estimation from Dependent Data
• Label-informed Graph Structure Learning for Node Classification
• FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping
• Towards a Taxonomy of Graph Learning Datasets