Explainable History Distillation by Marked Temporal Point Process.
CoRR(2023)
摘要
Explainability of machine learning models is mandatory when researchers
introduce these commonly believed black boxes to real-world tasks, especially
high-stakes ones. In this paper, we build a machine learning system to
automatically generate explanations of happened events from history by \gls{ca}
based on the \acrfull{tpp}. Specifically, we propose a new task called
\acrfull{ehd}. This task requires a model to distill as few events as possible
from observed history. The target is that the event distribution conditioned on
left events predicts the observed future noticeably worse. We then regard
distilled events as the explanation for the future. To efficiently solve
\acrshort{ehd}, we rewrite the task into a \gls{01ip} and directly estimate the
solution to the program by a model called \acrfull{model}. This work fills the
gap between our task and existing works, which only spot the difference between
factual and counterfactual worlds after applying a predefined modification to
the environment. Experiment results on Retweet and StackOverflow datasets prove
that \acrshort{model} significantly outperforms other \acrshort{ehd} baselines
and can reveal the rationale underpinning real-world processes.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要