GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks

Abstract

Node classification is an important research topic in graph learning. Graph neural networks (GNNs) have achieved state-of-the-art performance of node classification. However, existing GNNs address the problem where node samples for different classes are balanced; while for many real-world scenarios, some classes may have much fewer instances than others. Directly training a GNN classifier in this case would under-represent samples from those minority classes and result in sub-optimal performance. Therefore, it is very important to develop GNNs for imbalanced node classification. However, the work on this is rather limited. Hence, we seek to extend previous imbalanced learning techniques for i.i.d data to the imbalanced node classification task to facilitate GNN classifiers. In particular, we choose to adopt synthetic minority over-sampling algorithms, as they are found to be the most effective and stable. This task is non-trivial, as previous synthetic minority over-sampling algorithms fail to provide relation information for newly synthesized samples, which is vital for learning on graphs. Moreover, node attributes are high-dimensional. Directly over-sampling in the original input domain could generates out-of-domain samples, which may impair the accuracy of the classifier. We propose a novel framework, GraphSMOTE, in which an embedding space is constructed to encode the similarity among the nodes. New samples are synthesize in this space to assure genuineness. In addition, an edge generator is trained simultaneously to model the relation information, and provide it for those new samples. This framework is general and can be easily extended into different variations. The proposed framework is evaluated using three different datasets, and it outperforms all baselines with a large margin.

Accepted by WSDM2021

References in corpus (4)

• SMOTE: Synthetic Minority Over-sampling Technique
• A systematic study of the class imbalance problem in convolutional neural networks
• Object-Part Attention Model for Fine-grained Image Classification
• Network Embedding with Completely-imbalanced Labels

Cited by in corpus (21)

• A Comprehensive Survey on Deep Graph Representation Learning
• Graph Neural Networks for Financial Fraud Detection: A Review
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
• Towards Semi-supervised Universal Graph Classification
• A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges
• LTE4G: Long-Tail Experts for Graph Neural Networks
• Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
• Exploring Edge Disentanglement for Node Classification
• Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective
• Toward Degree Bias in Embedding-Based Knowledge Graph Completion
• MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution
• Towards Faithful and Consistent Explanations for Graph Neural Networks
• Counterfactual Learning on Graphs: A Survey
• Disambiguated Node Classification with Graph Neural Networks
• Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks
• A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
• S-Mixup: Structural Mixup for Graph Neural Networks
• Graph machine learning for flight delay prediction due to holding manouver
• INFLECT-DGNN: Influencer Prediction with Dynamic Graph Neural Networks
• Code Revert Prediction with Graph Neural Networks: A Case Study at J.P. Morgan Chase
• NodeImport: Imbalanced Node Classification with Node Importance Assessment