Semi-supervised Learning for Marked Temporal Point Processes

TL;DR

This paper introduces a semi-supervised learning algorithm for Marked Temporal Point Processes that leverages both labeled and unlabeled data, improving marker prediction accuracy in sequence modeling tasks.

Contribution

It presents a novel SSL algorithm for MTPP using RNN-based encoder-decoder architecture, addressing the gap in semi-supervised approaches for this domain.

Findings

Improved marker prediction performance over supervised methods

Effective representation learning with RNN encoder-decoder

Validated on Retweet dataset with positive results

Abstract

Temporal Point Processes (TPPs) are often used to represent the sequence of events ordered as per the time of occurrence. Owing to their flexible nature, TPPs have been used to model different scenarios and have shown applicability in various real-world applications. While TPPs focus on modeling the event occurrence, Marked Temporal Point Process (MTPP) focuses on modeling the category/class of the event as well (termed as the marker). Research in MTPP has garnered substantial attention over the past few years, with an extensive focus on supervised algorithms. Despite the research focus, limited attention has been given to the challenging problem of developing solutions in semi-supervised settings, where algorithms have access to a mix of labeled and unlabeled data. This research proposes a novel algorithm for Semi-supervised Learning for Marked Temporal Point Processes (SSL-MTPP) applicable in such scenarios. The proposed SSL-MTPP algorithm utilizes a combination of labeled and unlabeled data for learning a robust marker prediction model. The proposed algorithm utilizes an RNN-based Encoder-Decoder module for learning effective representations of the time sequence. The efficacy of the proposed algorithm has been demonstrated via multiple protocols on the Retweet dataset, where the proposed SSL-MTPP demonstrates improved performance in comparison to the traditional supervised learning approach.