Learning Point Processes using Recurrent Graph Network

08/11/2022
by   Saurabh Dash, et al.
22

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(N^2) (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.

READ FULL TEXT
research
03/30/2020

The Graph Hawkes Network for Reasoning on Temporal Knowledge Graphs

The Hawkes process has become a standard method for modeling self-exciti...
research
02/03/2022

Flexible Triggering Kernels for Hawkes Process Modeling

Recently proposed encoder-decoder structures for modeling Hawkes process...
research
03/30/2020

Graph Hawkes Network for Reasoning on Temporal Knowledge Graphs

The Hawkes process has become a standard method for modeling self-exciti...
research
05/05/2020

Event Cartography: Latent Point Process Embeddings

Many important phenomena arise naturally as temporal point processes wit...
research
11/15/2017

Crowd Counting Through Walls Using WiFi

Counting the number of people inside a building, from outside and withou...
research
12/31/2021

Transformer Embeddings of Irregularly Spaced Events and Their Participants

The neural Hawkes process (Mei Eisner, 2017) is a generative model o...
research
01/14/2019

Distributed Monitoring of Topological Events via Homology

Topological event detection allows for the distributed computation of ho...

Please sign up or login with your details

Forgot password? Click here to reset