mlsanityData to 14 Oct 2026

Learning Marked Temporal Point Process Explanations based on Counterfactual and Factual Reasoning

arXiv 2508.11943 ↗First posted 16 Aug 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural network-based Marked Temporal Point Process (MTPP) models have been widely adopted to model event sequences in high-stakes applications, raising concerns about the trustworthiness of outputs from these models. This study focuses on Explanation for MTPP, aiming to identify the minimal and rational explanation, that is, the minimum subset of events in history, based on which the prediction accuracy of MTPP matches that based on full history to a great extent and better than that based on the complement of the subset. This study finds that directly defining Explanation for MTPP as counterfactual explanation or factual explanation can result in irrational explanations. To address this issue, we define Explanation for MTPP as a combination of counterfactual explanation and factual explanation. This study proposes Counterfactual and Factual Explainer for MTPP (CFF) to solve Explanation for MTPP with a series of deliberately designed techniques. Experiments demonstrate the correctness and superiority of CFF over baselines regarding explanation quality and processing efficiency.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 38 of its 60 references that are in the map. First posted on arXiv 16 Aug 2025.

Builds on

38 of 60 references.

References · 38

  1. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  2. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  3. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  4. 2022Towards Reasoning in Large Language Models: A Surveycited by 596
  5. 2023Explainability for Large Language Models: A Surveycited by 333
  6. 2019Counterfactual Visual Explanationscited by 313
  7. 2016Rationalizing Neural Predictionscited by 281
  8. 2020Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Reviewcited by 174
  9. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  10. 2019Fully Neural Network based Model for General Temporal Point Processescited by 122
  11. 2021Neural Temporal Point Processes: A Reviewcited by 114
  12. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
26 more
  1. 2015SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularitycited by 76
  2. 2021Counterfactual Explainable Recommendationcited by 60
  3. 2019Imputing Missing Events in Continuous-Time Event Streamscited by 44
  4. 2022A Survey on Trustworthy Recommender Systemscited by 41
  5. 2020Neural Temporal Point Processes For Modelling Electronic Health Recordscited by 39
  6. 2019PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systemscited by 35
  7. 2021Counterfactual Graphs for Explainable Classification of Brain Networkscited by 33
  8. 2022A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challengescited by 30
  9. 2021Counterfactual Explanations for Neural Recommenderscited by 27
  10. 2022Fairness in Recommendation: Foundations, Methods and Applicationscited by 27
  11. 2023PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Predictioncited by 25
  12. 2016Generalized Inverse Classificationcited by 22
  13. 2019Synthesizing Action Sequences for Modifying Model Decisionscited by 22
  14. 2022GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendationscited by 22
  15. 2021Counterfactual Temporal Point Processescited by 20
  16. 2022Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Mediacited by 20
  17. 2024Decomposable Transformer Point Processescited by 16
  18. 2021VigDet: Knowledge Informed Neural Temporal Point Process for Coordination Detection on Social Mediacited by 14
  19. 2022Cardinality-Regularized Hawkes-Granger Modelcited by 14
  20. 2022On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approachcited by 11
  21. 2021Multi-objective Explanations of GNN Predictionscited by 10
  22. 2024Latent Logic Tree Extraction for Event Sequence Explanation from LLMscited by 9
  23. 2018Explainable time series tweaking via irreversible and reversible temporal transformationscited by 8
  24. 2024Learning Granger Causality from Instance-wise Self-attentive Hawkes Processescited by 7
  25. 2023Counterfactual Editing for Search Result Explanationcited by 6
  26. 2023Temporal Causal Mediation through a Point Process: Direct and Indirect Effects of Healthcare Interventionscited by 1

Built on by

Not cited yet.