Towards Anomaly Detection on Relational Data

2026/06/30 by Shiyuan Li, Yunfeng Zhao, Yue Tan +3
Computer Science · #cs.LG

paper · pdf

arxiv created 2026/08/01 · arxiv updated 2026/08/04

Abstract

Relational databases are widely used for managing structured data in real-world systems. Detecting anomalies from such relational data is crucial for identifying fraud, risks, and abnormal behaviors, yet remains under-explored. The key challenges lie in the intrinsic complexity of relational data: multi-table attributes are high-dimensional and heterogeneous, making sparse abnormal clues easy to overwhelm by normal or irrelevant information. Moreover, anomalies may further manifest as abnormal connection patterns across different foreign-key relations, which existing tabular and graph anomaly detection methods are ill-suited to capture. To address them, we propose RelAD, a reconstruction-based framework that captures anomalies from both attribute and relational edge reconstruction. RelAD contains two core modules: conditional sparse-gated attribute reconstruction, which suppresses redundant multi-table attributes and emphasizes abnormal semantic blocks, and dual-view multi-relational edge reconstruction, which detects relation-specific abnormal connections from both intrinsic and behavioral instance profiles. The resulting attribute and relational signals are integrated through a lightweight fusion module to produce the final anomaly score. We further construct 6 benchmark datasets with systematic anomalies, on which extensive experiments show that RelAD consistently outperforms baselines while achieving competitive efficiency..The source code is available at https://github.com/Shiy-Li/RelAD.

Citations

• PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models
• Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time
• Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data
• A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models
• FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
• Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation
• Relational Deep Learning: Challenges, Foundations and Next-Generation Architectures
• Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach
• Large Language Models are Good Relational Learners
• Relational Graph Transformer
• Griffin: Towards a Graph-Centric Relational Database Foundation Model
• A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detection
• Raising the Bar in Graph OOD Generalization: Invariant Learning Beyond Explicit Environment Modeling
• RelGNN: Composite Message Passing for Relational Deep Learning
• SALT: Sales Autocompletion Linked Business Tables Dataset
• Disentangling Tabular Data Towards Better One-Class Anomaly Detection
• Influence-oriented Personalized Federated Learning
• Deep Graph Anomaly Detection: A Survey and New Perspectives
• RelBench: A Benchmark for Deep Learning on Relational Databases
• SmoothGNN: Smoothing-aware GNN for Unsupervised Node Anomaly Detection
• ARC: A Generalist Graph Anomaly Detector with In-Context Learning
• Relational Deep Learning: Graph Representation Learning on Relational Databases
• PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection
• Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection
• Beyond Individual Input for Deep Anomaly Detection on Tabular Data
• Graph Anomaly Detection in Time Series: A Survey
• Data-Efficient and Interpretable Tabular Anomaly Detection
• LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks
• Deep Neural Networks and Tabular Data: A Survey
• Generative Adversarial Active Learning for Unsupervised Outlier Detection
• GRIFFIN
• Modeling Relational Data with Graph Convolutional Networks