Learning Graph Neural Networks with Positive and Unlabeled Nodes

Abstract

Graph neural networks (GNNs) are important tools for transductive learning tasks, such as node classification in graphs, due to their expressive power in capturing complex interdependency between nodes. To enable graph neural network learning, existing works typically assume that labeled nodes, from two or multiple classes, are provided, so that a discriminative classifier can be learned from the labeled data. In reality, this assumption might be too restrictive for applications, as users may only provide labels of interest in a single class for a small number of nodes. In addition, most GNN models only aggregate information from short distances (e.g., 1-hop neighbors) in each round, and fail to capture long distance relationship in graphs. In this paper, we propose a novel graph neural network framework, long-short distance aggregation networks (LSDAN), to overcome these limitations. By generating multiple graphs at different distance levels, based on the adjacency matrix, we develop a long-short distance attention model to model these graphs. The direct neighbors are captured via a short-distance attention mechanism, and neighbors with long distance are captured by a long distance attention mechanism. Two novel risk estimators are further employed to aggregate long-short-distance networks, for PU learning and the loss is back-propagated for model learning. Experimental results on real-world datasets demonstrate the effectiveness of our algorithm.

arXiv commentAccepted to ACM Transactions on Knowledge Discovery from Data (TKDD)

References in corpus (22)

• A Comprehensive Survey on Graph Neural Networks
• DeepWalk: Online Learning of Social Representations
• Semi-Supervised Classification with Graph Convolutional Networks
• LINE: Large-scale Information Network Embedding
• Inductive Representation Learning on Large Graphs
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Deep Convolutional Networks on Graph-Structured Data
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• Variational Graph Auto-Encoders
• Graph Transformer Networks
• Learning Graph Embedding with Adversarial Training Methods
• How Powerful are Graph Neural Networks?
• GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
• Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• Design Space for Graph Neural Networks
• Positive-Unlabeled Learning with Non-Negative Risk Estimator
• Adaptive Graph Convolutional Neural Networks
• Adversarially Regularized Graph Autoencoder for Graph Embedding
• Attributed Graph Clustering: A Deep Attentional Embedding Approach
• Graph Convolutional Networks for Classification with a Structured Label Space

Cited by in corpus (2)

• Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection
• Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming