Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling

TL;DR

This paper introduces an adversarial imitation learning framework for modeling high-dimensional latent dynamics in event sequences, effectively uncovering hidden marker networks and predicting future events without prior marker relation knowledge.

Contribution

It proposes a novel latent structural intensity model combined with an efficient sequence generation approach, addressing challenges in high-dimensional, multi-chain event data.

Findings

Successfully detects hidden marker networks

Accurately predicts future high-dimensional event sequences

Scales to millions of markers in real-world datasets

Abstract

We target modeling latent dynamics in high-dimension marked event sequences without any prior knowledge about marker relations. Such problem has been rarely studied by previous works which would have fundamental difficulty to handle the arisen challenges: 1) the high-dimensional markers and unknown relation network among them pose intractable obstacles for modeling the latent dynamic process; 2) one observed event sequence may concurrently contain several different chains of interdependent events; 3) it is hard to well define the distance between two high-dimension event sequences. To these ends, in this paper, we propose a seminal adversarial imitation learning framework for high-dimension event sequence generation which could be decomposed into: 1) a latent structural intensity model that estimates the adjacent nodes without explicit networks and learns to capture the temporal dynamics in the latent space of markers over observed sequence; 2) an efficient random walk based generation model that aims at imitating the generation process of high-dimension event sequences from a bottom-up view; 3) a discriminator specified as a seq2seq network optimizing the rewards to help the generator output event sequences as real as possible. Experimental results on both synthetic and real-world datasets demonstrate that the proposed method could effectively detect the hidden network among markers and make decent prediction for future marked events, even when the number of markers scales to million level.