CoDy: Counterfactual Explainers for Dynamic Graphs
Not on the map. Why?
Abstract (arXiv)
Temporal Graph Neural Networks (TGNNs) are widely used to model dynamic systems where relationships and features evolve over time. Although TGNNs demonstrate strong predictive capabilities in these domains, their complex architectures pose significant challenges for explainability. Counterfactual explanation methods provide a promising solution by illustrating how modifications to input graphs can influence model predictions. To address this challenge, we present CoDy, Counterfactual Explainer for Dynamic Graphs, a model-agnostic, instance-level explanation approach that identifies counterfactual subgraphs to interpret TGNN predictions. CoDy employs a search algorithm that combines Monte Carlo Tree Search with heuristic selection policies, efficiently exploring a vast search space of potential explanatory subgraphs by leveraging spatial, temporal, and local event impact information. Extensive experiments against state-of-the-art factual and counterfactual baselines demonstrate CoDy's effectiveness, with improvements of 16% in AUFSC+ over the strongest baseline.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 28 of its 38 references that are in the map. First posted on arXiv 25 Mar 2024.
Builds on
28 of 38 references.
References · 28
- 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
- 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
- 2020Inductive Representation Learning on Temporal Graphscited by 462
- 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 448
- 2020Parameterized Explainer for Graph Neural Networkcited by 426
- 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 401
- 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
- 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
- 2019Representation Learning for Dynamic Graphs: A Surveycited by 265
- 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
- 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 211
- 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
16 more
- 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
- 2019Explainability Techniques for Graph Convolutional Networkscited by 161
- 2023Towards Better Dynamic Graph Learning: New Architecture and Unified Librarycited by 157
- 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
- 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 138
- 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 119
- 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
- 2023Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunitiescited by 61
- 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 58
- 2022Provably expressive temporal graph networkscited by 56
- 2022A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challengescited by 30
- 2023DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networkscited by 27
- 2023TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discoverycited by 27
- 2021GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphscited by 13
- 2022An Explainer for Temporal Graph Neural Networkscited by 12
- 2024A Differential Geometric View and Explainability of GNN on Evolving Graphscited by 4
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.