Learning on Graphs with Out-of-Distribution Nodes

Abstract

Graph Neural Networks (GNNs) are state-of-the-art models for performing prediction tasks on graphs. While existing GNNs have shown great performance on various tasks related to graphs, little attention has been paid to the scenario where out-of-distribution (OOD) nodes exist in the graph during training and inference. Borrowing the concept from CV and NLP, we define OOD nodes as nodes with labels unseen from the training set. Since a lot of networks are automatically constructed by programs, real-world graphs are often noisy and may contain nodes from unknown distributions. In this work, we define the problem of graph learning with out-of-distribution nodes. Specifically, we aim to accomplish two tasks: 1) detect nodes which do not belong to the known distribution and 2) classify the remaining nodes to be one of the known classes. We demonstrate that the connection patterns in graphs are informative for outlier detection, and propose Out-of-Distribution Graph Attention Network (OODGAT), a novel GNN model which explicitly models the interaction between different kinds of nodes and separate inliers from outliers during feature propagation. Extensive experiments show that OODGAT outperforms existing outlier detection methods by a large margin, while being better or comparable in terms of in-distribution classification.

arXiv commentAccepted by KDD'22

References in corpus (8)

• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Pitfalls of Graph Neural Network Evaluation
• CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
• Uncertainty Aware Semi-Supervised Learning on Graph Data
• Entropic Out-of-Distribution Detection
• OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
• NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs

Cited by in corpus (6)

• Towards Semi-supervised Universal Graph Classification
• Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network
• Source Free Unsupervised Graph Domain Adaptation
• Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer
• Open-World Lifelong Graph Learning
• Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection