Learning Neural Models for Continuous-Time Sequences
This work addresses the problem of learning from continuous-time sequences for applications like online purchases and health records, but it appears incremental as it builds on existing MTPP methods.
The paper tackles the challenge of modeling continuous-time event sequences (CTES) with deep learning, proposing neural network-based models using marked temporal point processes (MTPP) to address issues like limited data and incomplete sequences, and reports efficacy over state-of-the-art baselines.
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.