Adaptive Graph Convolutional Neural Networks

Abstract

Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and connectivity. The paper proposes a generalized and flexible graph CNN taking data of arbitrary graph structure as input. In that way a task-driven adaptive graph is learned for each graph data while training. To efficiently learn the graph, a distance metric learning is proposed. Extensive experiments on nine graph-structured datasets have demonstrated the superior performance improvement on both convergence speed and predictive accuracy.

The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), 8 pages

References in corpus (11)

• Semi-Supervised Classification with Graph Convolutional Networks
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• Spectral Networks and Locally Connected Networks on Graphs
• Deep Convolutional Networks on Graph-Structured Data
• AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
• Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity
• Deep Learning with Dynamic Computation Graphs
• MoleculeNet: A Benchmark for Molecular Machine Learning
• Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
• Low Data Drug Discovery with One-shot Learning

Cited by in corpus (29)

• Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters
• Mining Latent Structures for Multimedia Recommendation
• DeeperGCN: All You Need to Train Deeper GCNs
• Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• Hierarchical Graph Pooling with Structure Learning
• TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
• Directed Graph Convolutional Network
• AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter
• Learning Graph Neural Networks with Positive and Unlabeled Nodes
• Tracklets Predicting Based Adaptive Graph Tracking
• DeepGS: Deep Representation Learning of Graphs and Sequences for Drug-Target Binding Affinity Prediction
• SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
• Sequential Recommendation with Graph Neural Networks
• DefenseVGAE: Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder
• Learning to Drop: Robust Graph Neural Network via Topological Denoising
• Stability and Generalization of Graph Convolutional Neural Networks
• Android Malware Detection using Large-scale Network Representation Learning
• LaplacianNet: Learning on 3D Meshes with Laplacian Encoding and Pooling
• Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning
• Graph Learning-Convolutional Networks
• Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning
• An Overview on the Application of Graph Neural Networks in Wireless Networks
• Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networks
• Graph Attribute Aggregation Network with Progressive Margin Folding
• Skeleton-based Hand-Gesture Recognition with Lightweight Graph Convolutional Networks
• GFCN: A New Graph Convolutional Network Based on Parallel Flows
• Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph Learning
• Multiple Graph Adversarial Learning
• Graph Partner Neural Networks for Semi-Supervised Learning on Graphs