mlsanityData to 14 Oct 2026

Robust Anomaly Detection Under Normality Distribution Shift in Dynamic Graphs

arXiv 2509.17400 ↗First posted 22 Sep 2025cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Anomaly detection in dynamic graphs is a critical task with broad real-world applications, including social networks, e-commerce, and cybersecurity. Most existing methods assume that normal patterns remain stable over time; however, this assumption often fails in practice due to the phenomenon we refer to as normality distribution shift (NDS), where normal behaviors evolve over time. Ignoring NDS can lead models to misclassify shifted normal instances as anomalies, degrading detection performance. To tackle this issue, we propose WhENDS, a novel unsupervised anomaly detection method that aligns normal edge embeddings across time by estimating distributional statistics and applying whitening transformations. Extensive experiments on four widely-used dynamic graph datasets show that WhENDS consistently outperforms nine strong baselines, achieving state-of-the-art results and underscoring the importance of addressing NDS in dynamic graph anomaly detection.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 19 of its 40 references that are in the map. First posted on arXiv 22 Sep 2025.

Builds on

19 of 40 references.

References · 19

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  4. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  5. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  6. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  7. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  8. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  9. 2021Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solutioncited by 157
  10. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  11. 2021Anomaly Detection in Dynamic Graphs via Transformercited by 59
  12. 2021Dynamic Graph Neural Networks for Sequential Recommendationcited by 57
7 more
  1. 2020Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphscited by 56
  2. 2018GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Predictioncited by 47
  3. 2023Neighbor Contrastive Learning on Learnable Graph Augmentationcited by 25
  4. 2022Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencodercited by 19
  5. 2024Spectral Invariant Learning for Dynamic Graphs under Distribution Shiftscited by 19
  6. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 17
  7. 2023Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environmentcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Feature-Context Consistency: Unsupervised Adversarial Detection with Drift Stability on Attributed Graphscited by 0