# TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery

arXiv: https://arxiv.org/abs/2310.19324 · HTML: https://mlsanity.com/paper/2310.19324/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 77 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Builds on (most cited first, 30 of 45)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [On Explainability of Graph Neural Networks via Subgraph Explorations](https://mlsanity.com/paper/2102.05152/) (2021)
- [XGNN: Towards Model-Level Explanations of Graph Neural Networks](https://mlsanity.com/paper/2006.02587/) (2020)
- [PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2010.05788/) (2020)
- [GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2001.06216/) (2020)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism](https://mlsanity.com/paper/2201.12987/) (2022)
- [Explainability Techniques for Graph Convolutional Networks](https://mlsanity.com/paper/1905.13686/) (2019)
- [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023)
- [ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations](https://mlsanity.com/paper/1911.07979/) (2019)
- [Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking](https://mlsanity.com/paper/2010.00577/) (2020)
- [Do We Really Need Complicated Model Architectures For Temporal Networks?](https://mlsanity.com/paper/2302.11636/) (2023)
- [Higher-Order Explanations of Graph Neural Networks via Relevant Walks](https://mlsanity.com/paper/2006.03589/) (2020)
- [ROLAND: Graph Learning Framework for Dynamic Graphs](https://mlsanity.com/paper/2208.07239/) (2022)
- [Towards Better Evaluation for Dynamic Link Prediction](https://mlsanity.com/paper/2207.10128/) (2022)
- [Higher-order organization of complex networks](https://mlsanity.com/paper/1612.08447/) (2016)
- [Motifs in Temporal Networks](https://mlsanity.com/paper/1612.09259/) (2016)

## Built on by (most cited first, 27 of 27)

- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices](https://mlsanity.com/paper/2502.04363/) (2025)
- [Explaining Graph Neural Networks via Structure-aware Interaction Index](https://mlsanity.com/paper/2405.14352/) (2024)
- [Learning High-Order Relationships of Brain Regions](https://mlsanity.com/paper/2312.02203/) (2023)
- [Exploring Causal Learning through Graph Neural Networks: An In-depth Review](https://mlsanity.com/paper/2311.14994/) (2023)
- [A Survey on Temporal Interaction Graph Representation Learning: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2505.04461/) (2025)
- [Are Large Language Models Good Temporal Graph Learners?](https://mlsanity.com/paper/2506.05393/) (2025)
- [CoDy: Counterfactual Explainers for Dynamic Graphs](https://mlsanity.com/paper/2403.16846/) (2024)
- [Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learning](https://mlsanity.com/paper/2407.00849/) (2024)
- [Studying and Improving Graph Neural Network-based Motif Estimation](https://mlsanity.com/paper/2506.15709/) (2025)
- [GRExplainer: A Universal Explanation Method for Temporal Graph Neural Networks](https://mlsanity.com/paper/2512.22772/) (2025)
- [Node Role-Guided LLMs for Dynamic Graph Clustering](https://mlsanity.com/paper/2603.13799/) (2026)
- [Poisson-Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs](https://mlsanity.com/paper/2607.02872/) (2026)
- [Where Does Neural Advantage Arise in Continuous-Time Dynamic Graph Prediction?](https://mlsanity.com/paper/2608.06765/) (2026)
- [MotifDisco: Motif Causal Discovery For Time Series Motifs](https://mlsanity.com/paper/2409.15219/) (2024)
- [STX-Search: Explanation Search for Continuous Dynamic Spatio-Temporal Models](https://mlsanity.com/paper/2503.04509/) (2025)
- [On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices](https://mlsanity.com/paper/2503.23796/) (2025)
- [Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning](https://mlsanity.com/paper/2508.14859/) (2025)
- [Debugging Tabular Log as Dynamic Graphs](https://mlsanity.com/paper/2512.22903/) (2025)
- [Stochastic Event Prediction via Temporal Motif Transitions](https://mlsanity.com/paper/2603.05874/) (2026)
- [ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability](https://mlsanity.com/paper/2605.19822/) (2026)
- [Temporal Motif Signatures for Temporal Graph Neural Networks](https://mlsanity.com/paper/2606.01176/) (2026)
- [Explaining Temporal Graph Neural Networks via Feature-induced Information Flow](https://mlsanity.com/paper/2606.27201/) (2026)
- [Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution](https://mlsanity.com/paper/2607.07716/) (2026)
- [Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors](https://mlsanity.com/paper/2608.15559/) (2026)
- [Statistical Feature Augmentation for Anomaly Detection in Dynamic Graphs](https://mlsanity.com/paper/2609.02965/) (2026)
- [From Explanations to Interventions: Execution-Guided Counterfactual Synthesis in Temporal Graphs](https://mlsanity.com/paper/2609.11170/) (2026)

## Abstract (arXiv)

Temporal graphs are widely used to model dynamic systems with time-varying interactions. In real-world scenarios, the underlying mechanisms of generating future interactions in dynamic systems are typically governed by a set of recurring substructures within the graph, known as temporal motifs. Despite the success and prevalence of current temporal graph neural networks (TGNN), it remains uncertain which temporal motifs are recognized as the significant indications that trigger a certain prediction from the model, which is a critical challenge for advancing the explainability and trustworthiness of current TGNNs. To address this challenge, we propose a novel approach, called Temporal Motifs Explainer (TempME), which uncovers the most pivotal temporal motifs guiding the prediction of TGNNs. Derived from the information bottleneck principle, TempME extracts the most interaction-related motifs while minimizing the amount of contained information to preserve the sparsity and succinctness of the explanation. Events in the explanations generated by TempME are verified to be more spatiotemporally correlated than those of existing approaches, providing more understandable insights. Extensive experiments validate the superiority of TempME, with up to 8.21% increase in terms of explanation accuracy across six real-world datasets and up to 22.96% increase in boosting the prediction Average Precision of current TGNNs.