Batch Virtual Adversarial Training for Graph Convolutional Networks

Abstract

We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs). BVAT addresses the shortcoming of GCNs that do not consider the smoothness of the model's output distribution against local perturbations around the input. We propose two algorithms, sample-based BVAT and optimization-based BVAT, which are suitable to promote the smoothness of the model for graph-structured data by either finding virtual adversarial perturbations for a subset of nodes far from each other or generating virtual adversarial perturbations for all nodes with an optimization process. Extensive experiments on three citation network datasets Cora, Citeseer and Pubmed and a knowledge graph dataset Nell validate the effectiveness of the proposed method, which establishes state-of-the-art results in the semi-supervised node classification tasks.

ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data

References in corpus (7)

• Inductive Representation Learning on Large Graphs
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Adversarial Attacks on Neural Networks for Graph Data
• Dropout Training as Adaptive Regularization
• Stochastic Training of Graph Convolutional Networks with Variance Reduction
• Adversarial Attack on Graph Structured Data
• Graph Partition Neural Networks for Semi-Supervised Classification

Cited by in corpus (20)

• Graph Contrastive Learning with Augmentations
• A Comprehensive Survey on Deep Graph Representation Learning
• Adversarial Attack and Defense on Graph Data: A Survey
• Graph Neural Networks: Taxonomy, Advances and Trends
• Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
• A Survey of Adversarial Learning on Graphs
• Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies
• Graph Random Neural Network for Semi-Supervised Learning on Graphs
• Local Augmentation for Graph Neural Networks
• Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective
• Calibrating and Improving Graph Contrastive Learning
• Tree Decomposed Graph Neural Network
• CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks
• LEReg: Empower Graph Neural Networks with Local Energy Regularization
• CGCL: Collaborative Graph Contrastive Learning without Handcrafted Graph Data Augmentations
• AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack
• Network representation learning: A macro and micro view
• Node Copying for Protection Against Graph Neural Network Topology Attacks
• Curvature Graph Neural Network
• On Generalization of Graph Autoencoders with Adversarial Training