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

TL;DR

This paper introduces OODHG, a novel method for detecting out-of-distribution nodes in heterogeneous graphs using energy propagation, addressing a gap in current GNN research for complex, real-world graph data.

Contribution

The paper proposes a new energy-based approach with meta-paths for OOD detection in heterogeneous graphs, improving accuracy and effectiveness over existing methods.

Findings

Outperforms baseline models in OOD detection accuracy.

Effectively classifies in-distribution nodes with high precision.

Demonstrates robustness across various heterogeneous graph datasets.

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.