arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.07797cs.LG
收藏

基于标记时间点过程的可解释历史蒸馏

Explainable History Distillation by Marked Temporal Point Process

RMIT University(皇家墨尔本理工大学);Macquarie University(麦考瑞大学)

Sishun Liu, Ke Deng, Yan Wang, Xiuzhen Zhang

AI总结:

本文提出可解释历史蒸馏任务,基于标记时间点过程将历史事件蒸馏为最小事件集以解释未来,并通过0-1整数规划高效求解,实验证明其优于基线。

摘要:

当研究人员将通常被认为是黑盒的机器学习模型引入现实世界任务,尤其是高风险任务时,模型的可解释性是强制性的。在本文中,我们基于标记时间点过程(TPP),构建了一个机器学习系统,利用因果分析(CA)自动为已发生事件生成解释。具体来说,我们提出了一个新任务,称为可解释历史蒸馏(EHD)。该任务要求模型从观测历史中蒸馏出尽可能少的事件,目标是使得在保留事件条件下的事件分布对观测未来的预测明显变差。然后,我们将蒸馏出的事件视为对未来的解释。为了高效解决EHD,我们将该任务改写为一个0-1整数规划(01IP)问题,并直接通过一个名为模型(MODEL)的模型来估计该规划的解。这项工作填补了我们的任务与现有工作之间的空白,现有工作仅通过在环境中应用预定义的修改来发现事实世界与反事实世界之间的差异。在Retweet和StackOverflow数据集上的实验结果表明,模型(MODEL)显著优于其他EHD基线方法,并能揭示现实世界过程背后的基本原理。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑