Imbalanced Graph-Level Anomaly Detection via Counterfactual Augmentation and Feature Learning

TL;DR

This paper introduces a novel imbalanced graph-level anomaly detection method that uses counterfactual augmentation and feature learning, improving detection accuracy by balancing datasets and leveraging additional graph features.

Contribution

The work proposes a counterfactual augmentation approach and a GNN-based feature learning module with adaptive weighting for improved imbalanced graph anomaly detection.

Findings

Enhanced detection performance on public datasets.

Robustness demonstrated through extensive experiments.

Effective generalization to brain disease datasets.

Abstract

Graph-level anomaly detection (GLAD) has already gained significant importance and has become a popular field of study, attracting considerable attention across numerous downstream works. The core focus of this domain is to capture and highlight the anomalous information within given graph datasets. In most existing studies, anomalies are often the instances of few. The stark imbalance misleads current GLAD methods to focus on learning the patterns of normal graphs more, further impacting anomaly detection performance. Moreover, existing methods predominantly utilize the inherent features of nodes to identify anomalous graph patterns which is approved suboptimal according to our experiments. In this work, we propose an imbalanced GLAD method via counterfactual augmentation and feature learning. Specifically, we first construct anomalous samples based on counterfactual learning, aiming to expand and balance the datasets. Additionally, we construct a module based on Graph Neural Networks (GNNs), which allows us to utilize degree attributes to complement the inherent attribute features of nodes. Then, we design an adaptive weight learning module to integrate features tailored to different datasets effectively to avoid indiscriminately treating all features as equivalent. Furthermore, extensive baseline experiments conducted on public datasets substantiate the robustness and effectiveness. Besides, we apply the model to brain disease datasets, which can prove the generalization capability of our work. The source code of our work is available online.