Robust Anomaly Detection with Graph Neural Networks using Controllability

2025-07-18

AI Summary

To address the challenge of limited anomalous samples and severe class imbalance in complex graph data—which hinder detection performance—this work introduces node average controllability into graph neural network (GNN)-based anomaly detection for the first time. We propose two novel integration mechanisms: incorporating average controllability as edge weights or as one-hot edge attribute vectors, thereby explicitly encoding each node’s structural influence under control-theoretic principles and enhancing GNNs’ discriminative capability for sparse anomalies. Our approach jointly leverages graph signal processing and relational modeling, and is trained end-to-end on both real-world and synthetic networks. Extensive experiments demonstrate that our method consistently outperforms six state-of-the-art baseline models across multiple benchmark datasets, achieving significant improvements in AUC and F1-score. These results validate average controllability as an effective and generalizable structural robustness prior for graph anomaly detection.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Anomaly detection in complex domains poses significant challenges due to the need for extensive labeled data and the inherently imbalanced nature of anomalous versus benign samples. Graph-based machine learning models have emerged as a promising solution that combines attribute and relational data to uncover intricate patterns. However, the scarcity of anomalous data exacerbates the challenge, which requires innovative strategies to enhance model learning with limited information. In this paper, we hypothesize that the incorporation of the influence of the nodes, quantified through average controllability, can significantly improve the performance of anomaly detection. We propose two novel approaches to integrate average controllability into graph-based frameworks: (1) using average controllability as an edge weight and (2) encoding it as a one-hot edge attribute vector. Through rigorous evaluation on real-world and synthetic networks with six state-of-the-art baselines, our proposed methods demonstrate improved performance in identifying anomalies, highlighting the critical role of controllability measures in enhancing the performance of graph machine learning models. This work underscores the potential of integrating average controllability as additional metrics to address the challenges of anomaly detection in sparse and imbalanced datasets.

Problem

• Detect anomalies in sparse, imbalanced graph data
• Enhance GNNs using controllability for anomaly detection
• Address labeled data scarcity in anomaly detection

Innovation

• Using average controllability as edge weight
• Encoding controllability as edge attribute
• Integrating controllability to enhance GNNs