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

Continuous-time long-term event prediction plays an important role in manyapplication scenarios. Most existing works rely on autoregressive frameworks topredict event sequences, which suffer from error accumulation, thuscompromising prediction quality. Inspired by the success of denoising diffusionprobabilistic models, we propose a diffusion-based non-autoregressive temporalpoint process model for long-term event prediction in continuous time. Insteadof generating events one at a time in an autoregressive way, our model predictsthe future event sequence entirely as a whole. In order to perform diffusionprocesses on event sequences, we develop a bidirectional map between targetevent sequences and the Euclidean vector space. Furthermore, we design a noveldenoising network to capture both sequential and contextual features for bettersample quality. Extensive experiments are conducted to prove the superiority ofour proposed model over state-of-the-art methods on long-term event predictionin continuous time. To the best of our knowledge, this is the first work toapply diffusion methods to long-term event prediction problems.

Non-Autoregressive Diffusion-based Temporal Point Processes for Continuous-Time Long-Term Event Prediction