Skip to main content
Learning Temporal Rules from Noisy Timeseries Data
  • Karan Samel, Georgia Tech, Georgia, USA
  • Zelin Zao, CUHK, Shenzhen, China
  • Binghong Chen, Georgia Tech, Georgia, USA
  • Shuang Li, CUHK, Shenzhen, China
  • Dharmashankar Subramanian, IBM Research AI
  • Irfan A. Essa, Georgia Tech, Google, Georgia, USA
  • Le Song, Biomap, Mohamed bin Zayed University of Artificial Intelligence, UAE
Document Type

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. © 2022, CC BY.

Publication Date
  • Common datum; Composite event; Data representations; Data settings; Logic rules; Temporal Data; Temporal modalities; Temporal ordering; Temporal rules; Time-series data

Preprints: arXiv

  • Archived with thanks to arXiv
  • Preprint License: CC by
  • Uploaded 24 March 2022
Citation Information
K. Samel, Z. Zhao, B. Chen, S. Li, D. Subramanian, I. Essa, and L. Song, "Learning temporal rules from noisy timeseries data," 2022, arXiv:2202.05403