mlsanityData to 7 Oct 2026

GLADformer: A Mixed Perspective for Graph-level Anomaly Detection

arXiv 2406.00734 ↗First posted 2 Jun 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph-Level Anomaly Detection (GLAD) aims to distinguish anomalous graphs within a graph dataset. However, current methods are constrained by their receptive fields, struggling to learn global features within the graphs. Moreover, most contemporary methods are based on spatial domain and lack exploration of spectral characteristics. In this paper, we propose a multi-perspective hybrid graph-level anomaly detector namely GLADformer, consisting of two key modules. Specifically, we first design a Graph Transformer module with global spectrum enhancement, which ensures balanced and resilient parameter distributions by fusing global features and spectral distribution characteristics. Furthermore, to uncover local anomalous attributes, we customize a band-pass spectral GNN message passing module that further enhances the model's generalization capability. Through comprehensive experiments on ten real-world datasets from multiple domains, we validate the effectiveness and robustness of GLADformer. This demonstrates that GLADformer outperforms current state-of-the-art models in graph-level anomaly detection, particularly in effectively capturing global anomaly representations and spectral characteristics.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 38 of its 52 references that are in the map. First posted on arXiv 2 Jun 2024.

Builds on

38 of 52 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2017Graph Attention Networkscited by 8,854
  7. 2018How Powerful are Graph Neural Networks?cited by 4,355
  8. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  9. 2021Rethinking Graph Transformers with Spectral Attentioncited by 468
  10. 2019Self-Attention Graph Poolingcited by 421
  11. 2019Provably Powerful Graph Networkscited by 385
  12. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
26 more
  1. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  2. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 185
  3. 2023Exphormer: Sparse Transformers for Graphscited by 166
  4. 2023Graph Inductive Biases in Transformers without Message Passingcited by 150
  5. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  6. 2020Line Graph Neural Networks for Link Predictioncited by 89
  7. 2019DeepGCNs: Making GCNs Go as Deep as CNNscited by 72
  8. 2022Hierarchical Graph Transformer with Adaptive Node Samplingcited by 72
  9. 2021Deep Graph-level Anomaly Detection by Glocal Knowledge Distillationcited by 67
  10. 2022Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented Viewcited by 54
  11. 2022Raising the Bar in Graph-level Anomaly Detectioncited by 45
  12. 2023PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Predictioncited by 44
  13. 2023Towards Self-Interpretable Graph-Level Anomaly Detectioncited by 41
  14. 2016Fast Memory-efficient Anomaly Detection in Streaming Heterogeneous Graphscited by 37
  15. 2023Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrumcited by 20
  16. 2023Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detectioncited by 19
  17. 2023Graph-level Anomaly Detection via Hierarchical Memory Networkscited by 16
  18. 2021A Broader Picture of Random-walk Based Graph Embeddingcited by 15
  19. 2023Contrastive Multi-view Subspace Clustering of Hyperspectral Images based on Graph Convolutional Networkscited by 11
  20. 2023Pixel-Superpixel Contrastive Learning and Pseudo-Label Correction for Hyperspectral Image Clusteringcited by 11
  21. 2022Learnable Spectral Wavelets on Dynamic Graphs to Capture Global Interactionscited by 10
  22. 2024CVTGAD: Simplified Transformer with Cross-View Attention for Unsupervised Graph-level Anomaly Detectioncited by 10
  23. 2023Few-shot Message-Enhanced Contrastive Learning for Graph Anomaly Detectioncited by 6
  24. 2017Metric Embedding via Shortest Path Decompositionscited by 2
  25. 2024Dual Graph Attention based Disentanglement Multiple Instance Learning for Brain Age Estimationcited by 2
  26. 2024SLFNet: Generating Semantic Logic Forms from Natural Language Using Semantic Probability Graphscited by 1

Built on by

Not cited yet.