Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation

Yiling Kuang, Chao Yang, Yang Yang, Shuang Li
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:2935-2943, 2024.

Abstract

In high-stakes systems such as healthcare, it is critical to understand the causal reasons behind unusual events, such as sudden changes in patient’s health. Unveiling the causal reasons helps with quick diagnoses and precise treatment planning. In this paper, we propose an automated method for uncovering “if-then” logic rules to explain observational events. We introduce {\it temporal point processes} to model the events of interest, and discover the set of latent rules to explain the occurrence of events. To achieve this goal, we employ an Expectation-Maximization (EM) algorithm. In the E-step, we calculate the posterior probability of each event being explained by each discovered rule. In the M-step, we update both the rule set and model parameters to enhance the likelihood function’s lower bound. Notably, we will optimize the rule set in a {\it differential} manner. Our approach demonstrates accurate performance in both discovering rules and identifying root causes. We showcase its promising results using synthetic and real healthcare datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v238-kuang24a, title = { Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation }, author = {Kuang, Yiling and Yang, Chao and Yang, Yang and Li, Shuang}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {2935--2943}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/kuang24a/kuang24a.pdf}, url = {https://proceedings.mlr.press/v238/kuang24a.html}, abstract = { In high-stakes systems such as healthcare, it is critical to understand the causal reasons behind unusual events, such as sudden changes in patient’s health. Unveiling the causal reasons helps with quick diagnoses and precise treatment planning. In this paper, we propose an automated method for uncovering “if-then” logic rules to explain observational events. We introduce {\it temporal point processes} to model the events of interest, and discover the set of latent rules to explain the occurrence of events. To achieve this goal, we employ an Expectation-Maximization (EM) algorithm. In the E-step, we calculate the posterior probability of each event being explained by each discovered rule. In the M-step, we update both the rule set and model parameters to enhance the likelihood function’s lower bound. Notably, we will optimize the rule set in a {\it differential} manner. Our approach demonstrates accurate performance in both discovering rules and identifying root causes. We showcase its promising results using synthetic and real healthcare datasets. } }
Endnote
%0 Conference Paper %T Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation %A Yiling Kuang %A Chao Yang %A Yang Yang %A Shuang Li %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-kuang24a %I PMLR %P 2935--2943 %U https://proceedings.mlr.press/v238/kuang24a.html %V 238 %X In high-stakes systems such as healthcare, it is critical to understand the causal reasons behind unusual events, such as sudden changes in patient’s health. Unveiling the causal reasons helps with quick diagnoses and precise treatment planning. In this paper, we propose an automated method for uncovering “if-then” logic rules to explain observational events. We introduce {\it temporal point processes} to model the events of interest, and discover the set of latent rules to explain the occurrence of events. To achieve this goal, we employ an Expectation-Maximization (EM) algorithm. In the E-step, we calculate the posterior probability of each event being explained by each discovered rule. In the M-step, we update both the rule set and model parameters to enhance the likelihood function’s lower bound. Notably, we will optimize the rule set in a {\it differential} manner. Our approach demonstrates accurate performance in both discovering rules and identifying root causes. We showcase its promising results using synthetic and real healthcare datasets.
APA
Kuang, Y., Yang, C., Yang, Y. & Li, S.. (2024). Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation . Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:2935-2943 Available from https://proceedings.mlr.press/v238/kuang24a.html.

Related Material