# Learning Point Processes using Recurrent Graph Network

arXiv: https://arxiv.org/abs/2208.05736 · HTML: https://mlsanity.com/paper/2208.05736/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 11 Aug 2022.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [Transformer Hawkes Process](https://mlsanity.com/paper/2002.09291/) (2020)
- [Intensity-Free Learning of Temporal Point Processes](https://mlsanity.com/paper/1909.12127/) (2019)
- [Lecture Notes: Temporal Point Processes and the Conditional Intensity Function](https://mlsanity.com/paper/1806.00221/) (2018)
- [Physics-Incorporated Convolutional Recurrent Neural Networks for Source Identification and Forecasting of Dynamical Systems](https://mlsanity.com/paper/2004.06243/) (2020)

## Built on by (most cited first, 2 of 2)

- [Interpretable Neural Temporal Point Processes for Modelling Electronic Health Records](https://mlsanity.com/paper/2404.08007/) (2024)
- [Cumulative Hazard Function Based Efficient Multivariate Temporal Point Process Learning](https://mlsanity.com/paper/2404.13663/) (2024)

## Abstract (arXiv)

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 O(N2) (total number of events) to O(|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.