Learning to Explore: Policy-Guided Outlier Synthesis for Graph Out-of-Distribution Detection
This addresses the safety and reliability of Graph Neural Networks for applications like anomaly detection, but it is incremental as it builds on existing outlier synthesis methods.
The paper tackles the problem of detecting out-of-distribution graphs in Graph Neural Networks by proposing a Policy-Guided Outlier Synthesis framework that replaces static sampling heuristics with a learned exploration strategy, achieving state-of-the-art performance on multiple benchmarks.
Detecting out-of-distribution (OOD) graphs is crucial for ensuring the safety and reliability of Graph Neural Networks. In unsupervised graph-level OOD detection, models are typically trained using only in-distribution (ID) data, resulting in incomplete feature space characterization and weak decision boundaries. Although synthesizing outliers offers a promising solution, existing approaches rely on fixed, non-adaptive sampling heuristics (e.g., distance- or density-based), limiting their ability to explore informative OOD regions. We propose a Policy-Guided Outlier Synthesis (PGOS) framework that replaces static heuristics with a learned exploration strategy. Specifically, PGOS trains a reinforcement learning agent to navigate low-density regions in a structured latent space and sample representations that most effectively refine the OOD decision boundary. These representations are then decoded into high-quality pseudo-OOD graphs to improve detector robustness. Extensive experiments demonstrate that PGOS achieves state-of-the-art performance on multiple graph OOD and anomaly detection benchmarks.