English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Temporal point process serves as an essential tool for modeling time-to-eventdata in continuous time space. Despite having massive amounts of event sequencedata from various domains like social media, healthcare etc., real worldapplication of temporal point process faces two major challenges: 1) it is notgeneralizable to predict events from unseen sequences in dynamic environment 2)they are not capable of thriving in continually evolving environment withminimal supervision while retaining previously learnt knowledge. To tacklethese issues, we propose \textit{HyperHawkes}, a hypernetwork based temporalpoint process framework which is capable of modeling time of occurrence ofevents for unseen sequences. Thereby, we solve the problem of zero-shotlearning for time-to-event modeling. We also develop a hypernetwork basedcontinually learning temporal point process for continuous modeling oftime-to-event sequences with minimal forgetting. In this way,\textit{HyperHawkes} augments the temporal point process with zero-shotmodeling and continual learning capabilities. We demonstrate the application ofthe proposed framework through our experiments on two real-world datasets. Ourresults show the efficacy of the proposed approach in terms of predictingfuture events under zero-shot regime for unseen event sequences. We also showthat the proposed model is able to predict sequences continually whileretaining information from previous event sequences, hence mitigatingcatastrophic forgetting for time-to-event data.

HyperHawkes: Hypernetwork based Neural Temporal Point Process