Adaptive Location Hierarchy Learning for Long-Tailed Mobility Prediction

TL;DR

This paper introduces ALOHA, an architecture-agnostic plugin that enhances long-tailed human mobility prediction by leveraging adaptive location hierarchies and a novel loss function, significantly improving prediction accuracy across models.

Contribution

The paper proposes the first architecture-agnostic plugin, ALOHA, which constructs city-specific location hierarchies using LLMs and introduces an adaptive loss to mitigate long-tailed bias in mobility prediction.

Findings

Improves long-tailed prediction accuracy by up to 16.59%.

Effectively captures high-level mobility semantics with minimal human effort.

Maintains efficiency and robustness across multiple models.

Abstract

Human mobility prediction is crucial for applications ranging from location-based recommendations to urban planning, which aims to forecast users' next location visits based on historical trajectories. While existing mobility prediction models excel at capturing sequential patterns through diverse architectures for different scenarios, they are hindered by the long-tailed distribution of location visits, leading to biased predictions and limited applicability. This highlights the need for a solution that enhances the long-tailed prediction capabilities of these models with broad compatibility and efficiency across diverse architectures. To address this need, we propose the first architecture-agnostic plugin for long-tailed human mobility prediction, named \textbf{A}daptive \textbf{LO}cation \textbf{H}ier\textbf{A}rchy learning (ALOHA). Inspired by Maslow's theory of human motivation, we exploit and explore common mobility knowledge of head and tail locations derived from human mobility trajectories to effectively mitigate long-tailed bias. Specifically, we introduce an automatic pipeline to construct city-tailored location hierarchies based on Large Language Models (LLMs) and Chain-of-Thought (CoT) prompts, capturing high-level mobility semantics with minimal human verification. We further design an Adaptive Hierarchical Loss (AHL) that rebalances learning through Gumbel disturbance and node-wise adaptive weighting, enabling both exploitation of multi-level signals and exploration within semantically related groups. Extensive experiments across multiple state-of-the-art models demonstrate that ALOHA consistently improves long-tailed mobility prediction performance by up to 16.59\% while maintaining efficiency and robustness. Our code is at https://github.com/Star607/ALOHA.