Related papers: HyperHawkes: Hypernetwork based Neural Temporal Point Process

HyperHawkes: Hypernetwork based Neural Temporal Point Process

URL: http://arxiv.org/abs/2210.00213v1
Date: Sat, 1 Oct 2022 07:14:19 GMT
Title: HyperHawkes: Hypernetwork based Neural Temporal Point Process
Authors: Manisha Dubey, P.K. Srijith, Maunendra Sankar Desarkar
Abstract summary: Temporal point process serves as an essential tool for modeling time-to-event data in continuous time space. It is not generalizable to predict events from unseen sequences in dynamic environment. We propose textitHyperHawkes, a hypernetwork based temporal point process framework.
Score: 5.607676459156789
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
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 faces two major challenges: 1) it is not generalizable to predict events from unseen sequences in dynamic environment 2) they are not capable of thriving in continually evolving environment with minimal supervision while retaining previously learnt knowledge. To tackle these issues, we propose \textit{HyperHawkes}, a hypernetwork based temporal point process framework which is capable of modeling time of occurrence of events for unseen sequences. Thereby, we solve the problem of zero-shot learning for time-to-event modeling. We also develop a hypernetwork based continually learning temporal point process for continuous modeling of time-to-event sequences with minimal forgetting. In this way, \textit{HyperHawkes} augments the temporal point process with zero-shot modeling and continual learning capabilities. We demonstrate the application of the proposed framework through our experiments on two real-world datasets. Our results show the efficacy of the proposed approach in terms of predicting future events under zero-shot regime for unseen event sequences. We also show that the proposed model is able to predict sequences continually while retaining information from previous event sequences, hence mitigating catastrophic forgetting for time-to-event data.