Meta Temporal Point Processes
This work addresses the challenge of improving TPP modeling for applications like event prediction, but it appears incremental as it builds on existing neural network and neural process methods.
The authors tackled the problem of modeling temporal point processes (TPPs) by proposing a meta-learning framework that treats each sequence as a different task, framing TPPs as neural processes with context sets and local history matching. They demonstrated the method on benchmark datasets and compared it with state-of-the-art TPP methods, though no concrete numbers are provided in the abstract.
A temporal point process (TPP) is a stochastic process where its realization is a sequence of discrete events in time. Recent work in TPPs model the process using a neural network in a supervised learning framework, where a training set is a collection of all the sequences. In this work, we propose to train TPPs in a meta learning framework, where each sequence is treated as a different task, via a novel framing of TPPs as neural processes (NPs). We introduce context sets to model TPPs as an instantiation of NPs. Motivated by attentive NP, we also introduce local history matching to help learn more informative features. We demonstrate the potential of the proposed method on popular public benchmark datasets and tasks, and compare with state-of-the-art TPP methods.