Learning Temporal Rules from Noisy Timeseries Data

TL;DR

This paper introduces Neural Temporal Logic Programming, a method that learns atomic event relations and rules from noisy temporal data, improving rule discovery in video and healthcare datasets.

Contribution

It presents a novel end-to-end differentiable approach to uncover temporal rules from composite event labels without explicit atomic event supervision.

Findings

Outperforms baseline methods in rule discovery tasks

Effective on video and healthcare datasets

Learns implicit temporal relations successfully

Abstract

Events across a timeline are a common data representation, seen in different temporal modalities. Individual atomic events can occur in a certain temporal ordering to compose higher level composite events. Examples of a composite event are a patient's medical symptom or a baseball player hitting a home run, caused distinct temporal orderings of patient vitals and player movements respectively. Such salient composite events are provided as labels in temporal datasets and most works optimize models to predict these composite event labels directly. We focus on uncovering the underlying atomic events and their relations that lead to the composite events within a noisy temporal data setting. We propose Neural Temporal Logic Programming (Neural TLP) which first learns implicit temporal relations between atomic events and then lifts logic rules for composite events, given only the composite events labels for supervision. This is done through efficiently searching through the combinatorial space of all temporal logic rules in an end-to-end differentiable manner. We evaluate our method on video and healthcare datasets where it outperforms the baseline methods for rule discovery.