Continual Learning for Time-to-Event Modeling

Manisha Dubey, PK Srijith, Maunendra Sankar Desarkar


Continual Lifelong Learning Workshop at ACML 2022
Paper

Abstract

Temporal point process serves as an essential tool for modeling time-to-event data in continuous time space. Despite having massive amounts of event sequence data from various domains like social media, healthcare etc., real world application of temporal point process are not capable of thriving in continually evolving environment with minimal supervision while retaining previously learnt knowledge. To tackle this, we propose HyperHawkes, a hypernetwork based continually learning temporal point process for continuous modeling of time-to-event sequences with minimal forgetting. We demonstrate the application of the proposed framework through our experiments on two real-world datasets.

Continual Learning for Time-to-Event Modeling image

BibTeX

@inproceedings{dubey2022continual,
    title     = {Continual Learning for Time-to-Event Modeling},
    author    = {Manisha Dubey and P. K. Srijith and Maunendra Sankar Desarkar},
    booktitle = {Continual Lifelong Learning Workshop at ACML 2022},
    year      = {2022},
    url       = {https://openreview.net/forum?id=1OHWaKZOub}
}