mlsanityData to 7 Oct 2026

A Generalizable Anomaly Detection Method in Dynamic Graphs

arXiv 2412.16447 ↗First posted 21 Dec 2024cs.LG cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Anomaly detection aims to identify deviations from normal patterns within data. This task is particularly crucial in dynamic graphs, which are common in applications like social networks and cybersecurity, due to their evolving structures and complex relationships. Although recent deep learning-based methods have shown promising results in anomaly detection on dynamic graphs, they often lack of generalizability. In this study, we propose GeneralDyG, a method that samples temporal ego-graphs and sequentially extracts structural and temporal features to address the three key challenges in achieving generalizability: Data Diversity, Dynamic Feature Capture, and Computational Cost. Extensive experimental results demonstrate that our proposed GeneralDyG significantly outperforms state-of-the-art methods on four real-world datasets.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 24 of its 43 references that are in the map. First posted on arXiv 21 Dec 2024.

Builds on

24 of 43 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  3. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  4. 2020A Generalization of Transformer Networks to Graphscited by 653
  5. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  6. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 521
  7. 2020Inductive Representation Learning on Temporal Graphscited by 454
  8. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
  9. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  10. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 248
  11. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  12. 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
12 more
  1. 2020Multivariate Time-series Anomaly Detection via Graph Attention Networkcited by 165
  2. 2021GraphiT: Encoding Graph Structure in Transformerscited by 146
  3. 2021Spatial-Temporal Transformer for Dynamic Scene Graph Generationcited by 95
  4. 2021TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learningcited by 65
  5. 2021Anomaly Detection in Dynamic Graphs via Transformercited by 57
  6. 2020Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphscited by 55
  7. 2022Hierarchical Local-Global Transformer for Temporal Sentence Groundingcited by 38
  8. 2019MIDAS: Microcluster-Based Detector of Anomalies in Edge Streamscited by 29
  9. 2023SAD: Semi-Supervised Anomaly Detection on Dynamic Graphscited by 27
  10. 2024On the Feasibility of Simple Transformer for Dynamic Graph Modelingcited by 22
  11. 2023Graph Anomaly Detection in Time Series: A Surveycited by 18
  12. 2024Anomaly Detection in Dynamic Graphs: A Comprehensive Surveycited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 4.

10 papers.

  1. 2025A Survey on Temporal Interaction Graph Representation Learning: Progress, Challenges, and Opportunitiescited by 4
  2. 2025A Smart Multimodal Healthcare Copilot with Powerful LLM Reasoningcited by 3
  3. 2025HyperEvent: A Strong Baseline for Dynamic Link Prediction via Relative Structural Encodingcited by 1
  4. 2025T3former: Temporal Graph Classification with Topological Machine Learningcited by 1
  5. 2025GLADMamba: Unsupervised Graph-Level Anomaly Detection Powered by Selective State Space Modelcited by 0
  6. 2025Are Heterogeneous Graph Neural Networks Truly Effective for Node Classification? A Causal Perspectivecited by 0
  7. 2026Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervisioncited by 0
  8. 2026Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Modelscited by 0
  9. 2026Neuromorphic Graph Anomaly Detection via Adaptive STDP and Spiking Graph Neural Networkscited by 0
  10. 2026Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detectioncited by 0