Learning Point Processes using Recurrent Graph Network

TL;DR

This paper introduces a Recurrent Graph Network that models complex event sequences using LSTM and attention mechanisms, improving efficiency and performance over existing Transformer-based methods.

Contribution

The paper proposes a novel RGN approach combining LSTM and GAT to efficiently learn point processes with reduced complexity and enhanced predictive accuracy.

Findings

Improved log-likelihood scores over baseline models

Lower time and space complexity compared to Transformers

Enhanced prediction and goodness-of-fit performance

Abstract

We present a novel Recurrent Graph Network (RGN) approach for predicting discrete marked event sequences by learning the underlying complex stochastic process. Using the framework of Point Processes, we interpret a marked discrete event sequence as the superposition of different sequences each of a unique type. The nodes of the Graph Network use LSTM to incorporate past information whereas a Graph Attention Network (GAT Network) introduces strong inductive biases to capture the interaction between these different types of events. By changing the self-attention mechanism from attending over past events to attending over event types, we obtain a reduction in time and space complexity from $\mathcal{O}(N^2)$ (total number of events) to $\mathcal{O}(|\mathcal{Y}|^2)$ (number of event types). Experiments show that the proposed approach improves performance in log-likelihood, prediction and goodness-of-fit tasks with lower time and space complexity compared to state-of-the art Transformer based architectures.