Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection

TL;DR

This paper introduces a novel graph OOD detection method called RSL that leverages feature resonance phenomena, showing that unknown ID samples change more during training, enabling effective OOD separation without label reliance.

Contribution

The paper proposes a new framework RSL that exploits feature resonance for OOD detection in graphs, including a practical proxy and synthetic OOD nodes, with theoretical error bounds.

Findings

RSL achieves state-of-the-art performance on 13 real-world datasets.

Feature resonance effectively separates OOD from ID nodes during training.

Theoretical analysis confirms superior OOD separability during resonance.

Abstract

Detecting out-of-distribution (OOD) nodes in the graph-based machine-learning field is challenging, particularly when in-distribution (ID) node multi-category labels are unavailable. Thus, we focus on feature space rather than label space and find that, ideally, during the optimization of known ID samples, unknown ID samples undergo more significant representation changes than OOD samples, even if the model is trained to fit random targets, which we called the Feature Resonance phenomenon. The rationale behind it is that even without gold labels, the local manifold may still exhibit smooth resonance. Based on this, we further develop a novel graph OOD framework, dubbed Resonance-based Separation and Learning (RSL), which comprises two core modules: (i) a more practical micro-level proxy of feature resonance that measures the movement of feature vectors in one training step. (ii) integrate with synthetic OOD nodes strategy to train an effective OOD classifier. Theoretically, we derive an error bound showing the superior separability of OOD nodes during the resonance period. Extensive experiments on a total of thirteen real-world graph datasets empirically demonstrate that RSL achieves state-of-the-art performance.