A Robust and Generalized Framework for Adversarial Graph Embedding
Graph embedding is essential for graph mining tasks. With the prevalence of graph data in real-world applications, many methods have been proposed in recent years to learn high-quality graph embedding vectors various types of graphs. However, most existing methods usually randomly select the negative samples from the original graph to enhance the training data without considering the noise. In addition, most of these methods only focus on the explicit graph structures and cannot fully capture complex semantics of edges such as various relationships or asymmetry. In order to address these issues, we propose a robust and generalized framework for adversarial graph embedding based on generative adversarial networks. Inspired by generative adversarial network, we propose a robust and generalized framework for adversarial graph embedding, named AGE. AGE generates the fake neighbor nodes as the enhanced negative samples from the implicit distribution, and enables the discriminator and generator to jointly learn each node's robust and generalized representation. Based on this framework, we propose three models to handle three types of graph data and derive the corresponding optimization algorithms, i.e., UG-AGE and DG-AGE for undirected and directed homogeneous graphs, respectively, and HIN-AGE for heterogeneous information networks. Extensive experiments show that our methods consistently and significantly outperform existing state-of-the-art methods across multiple graph mining tasks, including link prediction, node classification, and graph reconstruction.
Code (1)
Tasks
Generative Adversarial NetworkGraph EmbeddingGraph MiningGraph ReconstructionLink PredictionNode ClassificationSimilar Papers 제목 키워드 기반
Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge
With the success of the graph embedding model in both academic and industry areas, the robustness of graph embedding against adversarial attack inevitably becomes a crucial problem in graph learning. Existing works usual…
Adversarial AttackGraph EmbeddingGraph LearningA Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models
With the great success of graph embedding model on both academic and industry area, the robustness of graph embedding against adversarial attack inevitably becomes a central problem in graph learning domain. Regardless o…
Adversarial AttackGraph EmbeddingGraph LearningRepresentation LearningSPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation
A black-box spectral method is introduced for evaluating the adversarial robustness of a given machine learning (ML) model. Our approach, named SPADE, exploits bijective distance mapping between the input/output graphs c…
Adversarial RobustnessGraph EmbeddingAdversarially Regularized Graph Autoencoder for Graph Embedding
Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the …
ClusteringDecoderGraph ClusteringGraph Embedding+1Learning Graph Embedding with Adversarial Training Methods
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 o…
ClusteringDecoderGraph ClusteringGraph Embedding+2