Learning predictive checklists with probabilistic logic programming

TMLR Paper3053 Authors

Abstract: Checklists have been widely recognized as effective tools for completing complex tasks in a systematic manner. Although originally intended for use in procedural tasks, their interpretability and ease of use have led to their adoption for predictive tasks as well, including in clinical settings. However, designing checklists can be challenging, often requiring expert knowledge and manual rule design based on available data. Recent work has attempted to address this issue by using machine learning to automatically generate predictive checklists from data, although these approaches have been limited to Boolean data. We propose a novel method for learning predictive checklists from diverse data modalities, such as images and time series. Our approach relies on probabilistic logic programming, a learning paradigm that enables matching the discrete nature of checklist with continuous-valued data. We propose a regularization technique to tradeoff between the information captured in discrete concepts of continuous data and permit a tunable level of interpretability for the learned checklist concepts. We demonstrate that our method outperforms various explainable machine learning techniques on prediction tasks involving image sequences, medical time series, and clinical notes.

Submission Length: Regular submission (no more than 12 pages of main content)

Changes Since Last Submission:

In this revision, we have incorporated the feedback provided by Reviewer asA3, and all changes are highlighted in green. The changes are:
- Expanded the limitations section (Appendix L) of the paper to include parallel training as a future direction.
- Added Appendix F.6 to discuss how domain experts can validate the learnt concepts.

Assigned Action Editor: ~Alp_Kucukelbir1

Submission Number: 3053