CVAISep 20, 2020

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

arXiv:2009.09333v13 citations
Originality Highly original
AI Analysis

This addresses trajectory generation for mobility data applications, representing an incremental advance with novel method components.

The paper tackled the problem of generating realistic trajectory data by proposing factorized deep generative models that separate time-variant and time-invariant latent variables, and it achieved significant improvements in quantitative and qualitative evaluations.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes