Learning Graph Embedding with Adversarial Training Methods

Abstract

Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding distribution of the latent codes, which unfortunately may lead to inferior representation in many cases. In this paper, we present a novel adversarially regularized framework for graph embedding. By employing the graph convolutional network as an encoder, our framework embeds the topological information and node content into a vector representation, from which a graph decoder is further built to reconstruct the input graph. The adversarial training principle is applied to enforce our latent codes to match a prior Gaussian or Uniform distribution. Based on this framework, we derive two variants of adversarial models, the adversarially regularized graph autoencoder (ARGA) and its variational version, adversarially regularized variational graph autoencoder (ARVGA), to learn the graph embedding effectively. We also exploit other potential variations of ARGA and ARVGA to get a deeper understanding on our designs. Experimental results compared among twelve algorithms for link prediction and twenty algorithms for graph clustering validate our solutions.

arXiv commentTo appear in IEEE Transactions on Cybernetics. arXiv admin note: substantial text overlap with arXiv:1802.04407

References in corpus (16)

• Efficient Estimation of Word Representations in Vector Space
• Auto-Encoding Variational Bayes
• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• Graph Embedding Techniques, Applications, and Performance: A Survey
• Energy-based Generative Adversarial Network
• Variational Graph Auto-Encoders
• Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
• Adversarially Learned Inference
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• Attributed Social Network Embedding
• Attributed Network Embedding for Learning in a Dynamic Environment
• HARP: Hierarchical Representation Learning for Networks
• Deep Network Embedding for Graph Representation Learning in Signed Networks
• Semi-supervised Learning on Graphs with Generative Adversarial Nets
• Modeling documents with Generative Adversarial Networks

Cited by in corpus (37)

• A Survey on Deep Semi-supervised Learning
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
• Graph Learning: A Survey
• Graph-based Deep Learning for Communication Networks: A Survey
• Graph Convolutional Networks for Graphs Containing Missing Features
• Trustworthy Graph Neural Networks: Aspects, Methods and Trends
• Graph WaveNet for Deep Spatial-Temporal Graph Modeling
• Self-supervised Contrastive Attributed Graph Clustering
• Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering
• Attributed Graph Clustering: A Deep Attentional Embedding Approach
• CGC: Contrastive Graph Clustering for Community Detection and Tracking
• Learning Graph Neural Networks with Positive and Unlabeled Nodes
• Graph Neural Networks: Methods, Applications, and Opportunities
• NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Data
• Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming
• USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
• Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs
• Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors
• Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection
• Deep Graph Clustering via Mutual Information Maximization and Mixture Model
• CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering
• Hyperparameter-free and Explainable Whole Graph Embedding
• Unsupervised Deep Manifold Attributed Graph Embedding
• Deep Attention-guided Graph Clustering with Dual Self-supervision
• A Robust and Generalized Framework for Adversarial Graph Embedding
• Adversarial Directed Graph Embedding
• Attention-driven Graph Clustering Network
• Smoothness Sensor: Adaptive Smoothness-Transition Graph Convolutions for Attributed Graph Clustering
• ConTIG: Continuous Representation Learning on Temporal Interaction Graphs
• Multi-Level Graph Convolutional Network with Automatic Graph Learning for Hyperspectral Image Classification
• Deep Fusion Clustering Network
• Adversarial Learning with Cost-Sensitive Classes
• Latent Network Embedding via Adversarial Auto-encoders
• Graph Routing between Capsules
• Mutual Teaching for Graph Convolutional Networks
• GenURL: A General Framework for Unsupervised Representation Learning
• Self-Supervised Contrastive Graph Clustering Network via Structural Information Fusion