Multiple-level Point Embedding for Solving Human Trajectory Imputation with Prediction

TL;DR

This paper introduces a multi-level point embedding model that jointly improves human trajectory imputation and prediction by leveraging coexistence patterns and an innovative imputation cycle, demonstrating superior accuracy and stability.

Contribution

The work presents a novel multi-level embedding model with an imputation cycle that enhances joint trajectory imputation and prediction, addressing data sparsity issues.

Findings

Significant accuracy improvements over baselines in imputation and prediction.

Faster convergence due to the imputation cycle.

Robust performance across multiple real-world datasets.

Abstract

Sparsity is a common issue in many trajectory datasets, including human mobility data. This issue frequently brings more difficulty to relevant learning tasks, such as trajectory imputation and prediction. Nowadays, little existing work simultaneously deals with imputation and prediction on human trajectories. This work plans to explore whether the learning process of imputation and prediction could benefit from each other to achieve better outcomes. And the question will be answered by studying the coexistence patterns between missing points and observed ones in incomplete trajectories. More specifically, the proposed model develops an imputation component based on the self-attention mechanism to capture the coexistence patterns between observations and missing points among encoder-decoder layers. Meanwhile, a recurrent unit is integrated to extract the sequential embeddings from newly imputed sequences for predicting the following location. Furthermore, a new implementation called Imputation Cycle is introduced to enable gradual imputation with prediction enhancement at multiple levels, which helps to accelerate the speed of convergence. The experimental results on three different real-world mobility datasets show that the proposed approach has significant advantages over the competitive baselines across both imputation and prediction tasks in terms of accuracy and stability.