ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for Long-Term Cross-City Mobility Prediction

TL;DR

This paper introduces ST-MoE-BERT, a novel spatial-temporal mixture-of-experts framework that leverages BERT and transfer learning to improve long-term cross-city human mobility prediction, addressing data scarcity and complex dynamics.

Contribution

The paper presents a new model combining Mixture-of-Experts, BERT, and transfer learning for enhanced cross-city mobility prediction, outperforming existing methods.

Findings

Achieves 8.29% average improvement over state-of-the-art methods.

Effectively captures complex spatial-temporal mobility patterns.

Addresses data scarcity through transfer learning.

Abstract

Predicting human mobility across multiple cities presents significant challenges due to the complex and diverse spatial-temporal dynamics inherent in different urban environments. In this study, we propose a robust approach to predict human mobility patterns called ST-MoE-BERT. Compared to existing methods, our approach frames the prediction task as a spatial-temporal classification problem. Our methodology integrates the Mixture-of-Experts architecture with BERT model to capture complex mobility dynamics and perform the downstream human mobility prediction task. Additionally, transfer learning is integrated to solve the challenge of data scarcity in cross-city prediction. We demonstrate the effectiveness of the proposed model on GEO-BLEU and DTW, comparing it to several state-of-the-art methods. Notably, ST-MoE-BERT achieves an average improvement of 8.29%.