Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adaptive Location Hierarchy Learning for Long-Tailed Mobility Prediction

Yu Wang, Junshu Dai, Yuchen Ying, Yuxuan Liang, Tongya Zheng, Mingli Song

TL;DR

This work proposes the first plug-and-play framework for long-tailed mobility prediction in an exploitation and exploration manner, named ALOHA, which constructs city-tailored location hierarchy based on Large Language Models (LLMs) by exploiting Maslow's theory of human motivation to design Chain-of-Thought prompts that captures spatiotemporal semantics.

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. Despite the severe long-tailed distribution of locations, the problem of long-tailed mobility prediction remains largely underexplored. Existing long-tailed learning methods primarily focus on rebalancing the skewed distribution at the data, model, or class level, neglecting to exploit the spatiotemporal semantics of locations. To address this gap, we propose the first plug-and-play framework for long-tailed mobility prediction in an exploitation and exploration manner, named \textbf{A}daptive \textbf{LO}cation \textbf{H}ier\textbf{A}rchy learning (ALOHA). First, we construct city-tailored location hierarchy based on Large Language Models (LLMs) by exploiting Maslow's theory of human motivation to design Chain-of-Thought (CoT) prompts that captures spatiotemporal semantics. Second, we optimize the location hierarchy predictions by Gumbel disturbance and node-wise adaptive weights within the hierarchical tree structure. Experiments on state-of-the-art models across six datasets demonstrate the framework's consistent effectiveness and generalizability, which strikes a well balance between head and tail locations. Weight analysis and ablation studies reveal the optimization differences of each component for head and tail locations. Furthermore, in-depth analyses of hierarchical distance and case study demonstrate the effective semantic guidance from the location hierarchy. Our code will be made publicly available.

Adaptive Location Hierarchy Learning for Long-Tailed Mobility Prediction

TL;DR

This work proposes the first plug-and-play framework for long-tailed mobility prediction in an exploitation and exploration manner, named ALOHA, which constructs city-tailored location hierarchy based on Large Language Models (LLMs) by exploiting Maslow's theory of human motivation to design Chain-of-Thought prompts that captures spatiotemporal semantics.

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. Despite the severe long-tailed distribution of locations, the problem of long-tailed mobility prediction remains largely underexplored. Existing long-tailed learning methods primarily focus on rebalancing the skewed distribution at the data, model, or class level, neglecting to exploit the spatiotemporal semantics of locations. To address this gap, we propose the first plug-and-play framework for long-tailed mobility prediction in an exploitation and exploration manner, named \textbf{A}daptive \textbf{LO}cation \textbf{H}ier\textbf{A}rchy learning (ALOHA). First, we construct city-tailored location hierarchy based on Large Language Models (LLMs) by exploiting Maslow's theory of human motivation to design Chain-of-Thought (CoT) prompts that captures spatiotemporal semantics. Second, we optimize the location hierarchy predictions by Gumbel disturbance and node-wise adaptive weights within the hierarchical tree structure. Experiments on state-of-the-art models across six datasets demonstrate the framework's consistent effectiveness and generalizability, which strikes a well balance between head and tail locations. Weight analysis and ablation studies reveal the optimization differences of each component for head and tail locations. Furthermore, in-depth analyses of hierarchical distance and case study demonstrate the effective semantic guidance from the location hierarchy. Our code will be made publicly available.

Paper Structure

This paper contains 31 sections, 23 equations, 25 figures, 11 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Definition
  4. Methodology
  5. City-tailored Hierarchy Generation
  6. Adaptive Hierarchical Optimization
  7. Gradient Comparison of AHL and Cross-Entropy Loss
  8. Experiments
  9. Experimental Settings
  10. Main Results
  11. Further Analysis
  12. Conclusion
  13. Notations
  14. Supplement to Method
  15. Experimental Settings
  16. ...and 16 more sections

Figures (25)

  • Figure 1: The architecture of ALOHA for long-tailed mobility prediction.
  • Figure 1: Basic dataset statistics.
  • Figure 2: Statistics of locations in hierarchy.
  • Figure 3: MRR@$k$ and NDCG@$k$ comparison between ALOHA and SOTA baseline on JKT dataset.
  • Figure 4: Hierarchical distance comparison between ALOHA and SOTA baseline on JKT dataset.
  • ...and 20 more figures

Theorems & Definitions (3)

  • Definition 1: Trajectory
  • Definition 2: Head and Tail Locations
  • Definition 3: Mobility Prediction