Enhancing Fairness in Autoencoders for Node-Level Graph Anomaly Detection

TL;DR

This paper introduces DECAF-GAD, a novel autoencoder framework that improves fairness in node-level graph anomaly detection by disentangling sensitive attributes using a causal model, without sacrificing detection accuracy.

Contribution

The paper proposes a causal-disentangled autoencoder architecture with a fairness loss for unbiased graph anomaly detection, addressing fairness gaps in existing GAD methods.

Findings

DECAF-GAD achieves comparable anomaly detection performance to baseline methods.

It significantly improves fairness metrics across synthetic and real datasets.

The framework effectively disentangles sensitive attributes from learned representations.

Abstract

Graph anomaly detection (GAD) has become an increasingly important task across various domains. With the rapid development of graph neural networks (GNNs), GAD methods have achieved significant performance improvements. However, fairness considerations in GAD remain largely underexplored. Indeed, GNN-based GAD models can inherit and amplify biases present in training data, potentially leading to unfair outcomes. While existing efforts have focused on developing fair GNNs, most approaches target node classification tasks, where models often rely on simple layer architectures rather than autoencoder-based structures, which are the most widely used architecturs for anomaly detection. To address fairness in autoencoder-based GAD models, we propose \textbf{D}is\textbf{E}ntangled \textbf{C}ounterfactual \textbf{A}dversarial \textbf{F}air (DECAF)-GAD, a framework that alleviates bias while preserving GAD performance. Specifically, we introduce a structural causal model (SCM) to disentangle sensitive attributes from learned representations. Based on this causal framework, we formulate a specialized autoencoder architecture along with a fairness-guided loss function. Through extensive experiments on both synthetic and real-world datasets, we demonstrate that DECAF-GAD not only achieves competitive anomaly detection performance but also significantly enhances fairness metrics compared to baseline GAD methods. Our code is available at https://github.com/Tlhey/decaf_code.