Graph Anomaly Detection via Adaptive Test-time Representation Learning across Out-of-Distribution Domains

2025-02-20

AI Summary

To address the failure of supervised methods in cross-domain graph anomaly detection (GAD) caused by distribution shift and feature heterogeneity, this paper proposes AdaGraph-T3—a novel framework enabling test-time domain adaptation solely via self-supervision. Its key contributions are: (1) a test-time adaptive mechanism grounded in node homophily affinity; (2) edge-attention-weighted message passing to enhance structural awareness; and (3) domain-specific encoders jointly optimized with class-aware regularization to improve cross-domain generalization and robustness to long-tailed anomalies. The framework integrates supervised or self-supervised pretraining with test-time self-supervised fine-tuning. Evaluated on multiple cross-domain benchmarks, AdaGraph-T3 achieves average improvements of 6.6% in AUROC and 7.9% in AUPRC over state-of-the-art methods, demonstrating superior performance and generalizability.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Graph Anomaly Detection (GAD) has demonstrated great effectiveness in identifying unusual patterns within graph-structured data. However, while labeled anomalies are often scarce in emerging applications, existing supervised GAD approaches are either ineffective or not applicable when moved across graph domains due to distribution shifts and heterogeneous feature spaces. To address these challenges, we present AdaGraph-T3, a novel test-time training framework for cross-domain GAD. AdaGraph-T3 combines supervised and self-supervised learning during training while adapting to a new domain during test time using only self-supervised learning by leveraging a homophily-based affinity score that captures domain-invariant properties of anomalies. Our framework introduces four key innovations to cross-domain GAD: an effective self-supervision scheme, an attention-based mechanism that dynamically learns edge importance weights during message passing, domain-specific encoders for handling heterogeneous features, and class-aware regularization to address imbalance. Experiments across multiple cross-domain settings demonstrate that AdaGraph-T3 significantly outperforms existing approaches, achieving average improvements of over 6.6% in AUROC and 7.9% in AUPRC compared to the best competing model.

Problem

• Detects anomalies in graph-structured data.
• Adapts to new domains during test time.
• Handles distribution shifts and heterogeneous features.

Innovation

• Adaptive test-time training framework
• Self-supervised learning for domain adaptation
• Attention-based edge importance mechanism