mlsanityData to 7 Oct 2026

Event Detection on Dynamic Graphs

arXiv 2110.12148 ↗First posted 23 Oct 2021cs.LG cs.SIcited by 4

Not on the map. Why?

Abstract (arXiv)

Event detection is a critical task for timely decision-making in graph analytics applications. Despite the recent progress towards deep learning on graphs, event detection on dynamic graphs presents particular challenges to existing architectures. Real-life events are often associated with sudden deviations of the normal behavior of the graph. However, existing approaches for dynamic node embedding are unable to capture the graph-level dynamics related to events. In this paper, we propose DyGED, a simple yet novel deep learning model for event detection on dynamic graphs. DyGED learns correlations between the graph macro dynamics -- i.e. a sequence of graph-level representations -- and labeled events. Moreover, our approach combines structural and temporal self-attention mechanisms to account for application-specific node and time importances effectively. Our experimental evaluation, using a representative set of datasets, demonstrates that DyGED outperforms competing solutions in terms of event detection accuracy by up to 8.5% while being more scalable than the top alternatives. We also present case studies illustrating key features of our model.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 28 of its 62 references that are in the map. First posted on arXiv 23 Oct 2021.

Builds on

28 of 62 references.

References · 28

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  7. 2019Attention is not Explanationcited by 916
  8. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  9. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  10. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  11. 2019Attention is not not Explanationcited by 629
  12. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
16 more
  1. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 399
  2. 2016Learning Convolutional Neural Networks for Graphscited by 314
  3. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 273
  4. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  5. 2019A Survey on Graph Kernelscited by 148
  6. 2020Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A surveycited by 123
  7. 2019Learning to Deceive with Attention-Based Explanationscited by 111
  8. 2020The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabelingcited by 64
  9. 2019Semi-Supervised Graph Classification: A Hierarchical Graph Perspectivecited by 55
  10. 2019Temporal Network Embedding with Micro- and Macro-dynamicscited by 51
  11. 2019Node Embedding over Temporal Graphscited by 45
  12. 2019Recurrent Space-time Graph Neural Networkscited by 19
  13. 2014Detecting change points in the large-scale structure of evolving networkscited by 13
  14. 2014'Beating the news' with EMBERS: Forecasting Civil Unrest using Open Source Indicatorscited by 10
  15. 2015Less is More: Building Selective Anomaly Ensemblescited by 3
  16. 2016Social Networks Under Stresscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2.

4 papers.

  1. 2022Global Counterfactual Explainer for Graph Neural Networkscited by 30
  2. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  3. 2023GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarkingcited by 11
  4. 2022Incorporating Heterophily into Graph Neural Networks for Graph Classificationcited by 4