Learning Neural Models for Continuous-Time Sequences

TL;DR

This paper explores neural models for continuous-time event sequences, addressing challenges like data limitations and sequence complexity by leveraging marked temporal point processes to improve modeling and prediction.

Contribution

It introduces scalable neural network models based on marked temporal point processes for continuous-time sequences, highlighting their robustness and effectiveness over existing methods.

Findings

Proposed models outperform state-of-the-art baselines.

Models effectively handle incomplete and limited data.

Demonstrated scalability to large datasets.

Abstract

The large volumes of data generated by human activities such as online purchases, health records, spatial mobility etc. are stored as a sequence of events over a continuous time. Learning deep learning methods over such sequences is a non-trivial task as it involves modeling the ever-increasing event timestamps, inter-event time gaps, event types, and the influences between events -- within and across different sequences. This situation is further exacerbated by the constraints associated with data collection e.g. limited data, incomplete sequences, privacy restrictions etc. With the research direction described in this work, we aim to study the properties of continuous-time event sequences (CTES) and design robust yet scalable neural network-based models to overcome the aforementioned problems. In this work, we model the underlying generative distribution of events using marked temporal point processes (MTPP) to address a wide range of real-world problems. Moreover, we highlight the efficacy of the proposed approaches over the state-of-the-art baselines and later report the ongoing research problems.