Mixture-of-Experts for Personalized and Semantic-Aware Next Location Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Shuai, Cao, Ning, Chen, Yile, Jiang, Yue, Cong, Gao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909629343072256
author Liu, Shuai
Cao, Ning
Chen, Yile
Jiang, Yue
Cong, Gao
author_facet Liu, Shuai
Cao, Ning
Chen, Yile
Jiang, Yue
Cong, Gao
contents Next location prediction plays a critical role in understanding human mobility patterns. However, existing approaches face two core limitations: (1) they fall short in capturing the complex, multi-functional semantics of real-world locations; and (2) they lack the capacity to model heterogeneous behavioral dynamics across diverse user groups. To tackle these challenges, we introduce NextLocMoE, a novel framework built upon large language models (LLMs) and structured around a dual-level Mixture-of-Experts (MoE) design. Our architecture comprises two specialized modules: a Location Semantics MoE that operates at the embedding level to encode rich functional semantics of locations, and a Personalized MoE embedded within the Transformer backbone to dynamically adapt to individual user mobility patterns. In addition, we incorporate a history-aware routing mechanism that leverages long-term trajectory data to enhance expert selection and ensure prediction stability. Empirical evaluations across several real-world urban datasets show that NextLocMoE achieves superior performance in terms of predictive accuracy, cross-domain generalization, and interpretability
format Preprint
id arxiv_https___arxiv_org_abs_2505_24597
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mixture-of-Experts for Personalized and Semantic-Aware Next Location Prediction
Liu, Shuai
Cao, Ning
Chen, Yile
Jiang, Yue
Cong, Gao
Artificial Intelligence
Next location prediction plays a critical role in understanding human mobility patterns. However, existing approaches face two core limitations: (1) they fall short in capturing the complex, multi-functional semantics of real-world locations; and (2) they lack the capacity to model heterogeneous behavioral dynamics across diverse user groups. To tackle these challenges, we introduce NextLocMoE, a novel framework built upon large language models (LLMs) and structured around a dual-level Mixture-of-Experts (MoE) design. Our architecture comprises two specialized modules: a Location Semantics MoE that operates at the embedding level to encode rich functional semantics of locations, and a Personalized MoE embedded within the Transformer backbone to dynamically adapt to individual user mobility patterns. In addition, we incorporate a history-aware routing mechanism that leverages long-term trajectory data to enhance expert selection and ensure prediction stability. Empirical evaluations across several real-world urban datasets show that NextLocMoE achieves superior performance in terms of predictive accuracy, cross-domain generalization, and interpretability
title Mixture-of-Experts for Personalized and Semantic-Aware Next Location Prediction
topic Artificial Intelligence
url https://arxiv.org/abs/2505.24597