Out-of-Distribution Detection in Heterogeneous Graphs via Energy Propagation

2025-04-29

AI Summary

This paper addresses the underexplored problem of out-of-distribution (OOD) node detection in heterogeneous graphs. We propose EnergyProp, the first dedicated OOD detection framework for heterogeneous graphs, built upon heterogeneous graph neural networks and meta-path-guided representation learning. EnergyProp explicitly models heterogeneous structural semantics by designing an energy score estimator and an energy-constrained optimization strategy to sharpen the decision boundary between in-distribution (ID) and OOD nodes. Furthermore, it introduces energy propagation to iteratively select high-confidence ID nodes, enabling joint optimization of OOD detection and ID classification. Extensive experiments on multiple real-world heterogeneous graph benchmarks demonstrate that EnergyProp achieves up to a 12.3% improvement in AUROC over state-of-the-art baselines, while maintaining high ID classification accuracy. To our knowledge, this is the first work to systematically formulate and solve the OOD detection problem in heterogeneous graphs.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Graph neural networks (GNNs) are proven effective in extracting complex node and structural information from graph data. While current GNNs perform well in node classification tasks within in-distribution (ID) settings, real-world scenarios often present distribution shifts, leading to the presence of out-of-distribution (OOD) nodes. OOD detection in graphs is a crucial and challenging task. Most existing research focuses on homogeneous graphs, but real-world graphs are often heterogeneous, consisting of diverse node and edge types. This heterogeneity adds complexity and enriches the informational content. To the best of our knowledge, OOD detection in heterogeneous graphs remains an underexplored area. In this context, we propose a novel methodology for OOD detection in heterogeneous graphs (OODHG) that aims to achieve two main objectives: 1) detecting OOD nodes and 2) classifying all ID nodes based on the first task's results. Specifically, we learn representations for each node in the heterogeneous graph, calculate energy values to determine whether nodes are OOD, and then classify ID nodes. To leverage the structural information of heterogeneous graphs, we introduce a meta-path-based energy propagation mechanism and an energy constraint to enhance the distinction between ID and OOD nodes. Extensive experimental findings substantiate the simplicity and effectiveness of OODHG, demonstrating its superiority over baseline models in OOD detection tasks and its accuracy in ID node classification.

Problem

• Detecting OOD nodes in heterogeneous graphs using energy propagation
• Classifying in-distribution nodes based on OOD detection results
• Enhancing ID-OOD distinction via meta-path energy propagation

Innovation

• Energy-based OOD detection in heterogeneous graphs
• Meta-path-based energy propagation mechanism
• Energy constraint enhances ID-OOD distinction