Factorized Deep Generative Models for Trajectory Generation with Spatiotemporal-Validity Constraints

TL;DR

This paper introduces novel deep generative models for trajectory data that factorize latent variables and incorporate spatiotemporal validity constraints, improving generation quality and interpretability.

Contribution

It proposes a new factorized deep generative framework with specialized inference strategies and neural architectures for more accurate and valid trajectory generation.

Findings

Significant improvements in quantitative evaluation metrics.

Enhanced qualitative realism of generated trajectories.

Effective modeling of global and local semantic patterns.

Abstract

Trajectory data generation is an important domain that characterizes the generative process of mobility data. Traditional methods heavily rely on predefined heuristics and distributions and are weak in learning unknown mechanisms. Inspired by the success of deep generative neural networks for images and texts, a fast-developing research topic is deep generative models for trajectory data which can learn expressively explanatory models for sophisticated latent patterns. This is a nascent yet promising domain for many applications. We first propose novel deep generative models factorizing time-variant and time-invariant latent variables that characterize global and local semantics, respectively. We then develop new inference strategies based on variational inference and constrained optimization to encapsulate the spatiotemporal validity. New deep neural network architectures have been developed to implement the inference and generation models with newly-generalized latent variable priors. The proposed methods achieved significant improvements in quantitative and qualitative evaluations in extensive experiments.