Evidential Spectrum-Aware Contrastive Learning for OOD Detection in Dynamic Graphs

TL;DR

This paper introduces EviSEC, a novel evidential spectrum-aware contrastive learning method for out-of-distribution detection in dynamic graphs, addressing bias, variance, and score homogenization issues.

Contribution

It proposes an evidential neural network with spectrum-aware augmentation to improve OOD detection by widening score gaps and modeling uncertainty more effectively.

Findings

EviSEC outperforms existing methods on real-world datasets.

The approach effectively distinguishes ID and OOD data in dynamic graphs.

Uncertainty modeling enhances detection robustness.

Abstract

Recently, Out-of-distribution (OOD) detection in dynamic graphs, which aims to identify whether incoming data deviates from the distribution of the in-distribution (ID) training set, has garnered considerable attention in security-sensitive fields. Current OOD detection paradigms primarily focus on static graphs and confront two critical challenges: i) high bias and high variance caused by single-point estimation, which makes the predictions sensitive to randomness in the data; ii) score homogenization resulting from the lack of OOD training data, where the model only learns ID-specific patterns, resulting in overall low OOD scores and a narrow score gap between ID and OOD data. To tackle these issues, we first investigate OOD detection in dynamic graphs through the lens of Evidential Deep Learning (EDL). Specifically, we propose EviSEC, an innovative and effective OOD detector via Evidential Spectrum-awarE Contrastive Learning. We design an evidential neural network to redefine the output as the posterior Dirichlet distribution, explaining the randomness of inputs through the uncertainty of distribution, which is overlooked by single-point estimation. Moreover, spectrum-aware augmentation module generates OOD approximations to identify patterns with high OOD scores, thereby widening the score gap between ID and OOD data and mitigating score homogenization. Extensive experiments on real-world datasets demonstrate that EviSAC effectively detects OOD samples in dynamic graphs.