TY - GEN
T1 - Learning marked temporal point process explanations based on counterfactual and factual reasoning
AU - Liu, Sishun
AU - Deng, Ke
AU - Zhang, Xiuzhen
AU - Wang, Yan
N1 - Copyright the Author(s) 2025. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.
PY - 2025
Y1 - 2025
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/105024443441
U2 - 10.3233/FAIA251016
DO - 10.3233/FAIA251016
M3 - Conference proceeding contribution
AN - SCOPUS:105024443441
T3 - Frontiers in Artificial Intelligence and Applications
SP - 1841
EP - 1848
BT - ECAI 2025
A2 - Lynce, Inês
A2 - Murano, Nello
A2 - Vallati, Mauro
A2 - Villata, Serena
A2 - Chesani, Federico
A2 - Milano, Michela
A2 - Omicini, Andrea
A2 - Dastani, Mehdi
PB - IOS Press
CY - Amsterdam
T2 - 28th European Conference on Artificial Intelligence, ECAI 2025, including 14th Conference on Prestigious Applications of Intelligent Systems, PAIS 2025
Y2 - 25 October 2025 through 30 October 2025
ER -