Efficient Temporal Tokenization for Mobility Prediction with Large Language Models

TL;DR

RHYTHM introduces a hierarchical temporal tokenization framework leveraging large language models for efficient and accurate human mobility prediction, capturing multi-scale dependencies with reduced computational costs.

Contribution

The paper presents a novel hierarchical tokenization method that enables LLMs to effectively model spatio-temporal mobility data with enhanced efficiency and accuracy.

Findings

Achieved 2.4% accuracy improvement over state-of-the-art methods.

Reduced training time by 24.6%.

Improved weekend prediction accuracy by 5.0%.

Abstract

We introduce RHYTHM (Reasoning with Hierarchical Temporal Tokenization for Human Mobility), a framework that leverages large language models (LLMs) as spatio-temporal predictors and trajectory reasoners. RHYTHM partitions trajectories into daily segments encoded as discrete tokens with hierarchical attention, capturing both daily and weekly dependencies while substantially reducing the sequence length. Token representations are enriched with pre-computed prompt embeddings via a frozen LLM, enhancing the model's ability to capture interdependencies without extensive computational overhead. By freezing the LLM backbone, RHYTHM achieves significant computational efficiency. Evaluation on three real-world datasets demonstrates a 2.4% improvement in accuracy, 5.0% increase on weekends, and 24.6% reduction in training time compared to state-of-the-art methods.