Pathlet Variational Auto-Encoder for Robust Trajectory Generation

2025-11-20

AI Summary

To address the limited noise robustness and interpretability of urban trajectory generation models, this paper proposes a variational generative framework based on binary pathlet representations. Methodologically, it integrates a variational autoencoder with a linear decoder, incorporating a learnable pathlet dictionary and a probabilistic graph modeling mechanism to explicitly characterize the trajectory generation process, enabling conditional generation and end-to-end joint optimization. Key contributions include: (i) binary pathlet encoding, which enhances semantic interpretability; and (ii) a probabilistic architecture designed to jointly balance robustness to input noise, computational efficiency, and compatibility with downstream tasks. Evaluated on two real-world datasets, the model achieves average improvements of 35.4% and 26.3% over strong baselines, reduces training time by 64.8%, and cuts GPU memory usage by 56.5%. Moreover, it effectively supports downstream applications such as trajectory prediction and denoising.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Motion and Path Planning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Trajectory generation has recently drawn growing interest in privacy-preserving urban mobility studies and location-based service applications. Although many studies have used deep learning or generative AI methods to model trajectories and have achieved promising results, the robustness and interpretability of such models are largely unexplored. This limits the application of trajectory generation algorithms on noisy real-world data and their trustworthiness in downstream tasks. To address this issue, we exploit the regular structure in urban trajectories and propose a deep generative model based on the pathlet representation, which encode trajectories with binary vectors associated with a learned dictionary of trajectory segments. Specifically, we introduce a probabilistic graphical model to describe the trajectory generation process, which includes a Variational Autoencoder (VAE) component and a linear decoder component. During training, the model can simultaneously learn the latent embedding of pathlet representations and the pathlet dictionary that captures mobility patterns in the trajectory dataset. The conditional version of our model can also be used to generate customized trajectories based on temporal and spatial constraints. Our model can effectively learn data distribution even using noisy data, achieving relative improvements of $35.4%$ and $26.3%$ over strong baselines on two real-world trajectory datasets. Moreover, the generated trajectories can be conveniently utilized for multiple downstream tasks, including trajectory prediction and data denoising. Lastly, the framework design offers a significant efficiency advantage, saving $64.8%$ of the time and $56.5%$ of GPU memory compared to previous approaches.

Problem

• Addressing robustness and interpretability limitations in trajectory generation models
• Learning mobility patterns from noisy urban trajectory data efficiently
• Generating customized trajectories with spatial-temporal constraints for downstream tasks

Innovation

• Pathlet-based variational autoencoder for trajectory generation
• Probabilistic graphical model with VAE and linear decoder
• Learns latent embeddings and pathlet dictionary from noisy data