Beyond Long Tail POIs: Transition-Centered Generalization for Human Mobility Prediction

TL;DR

This paper addresses the challenge of predicting human mobility to long-tail POIs by proposing a transition reconstruction framework that enhances generalization and improves prediction accuracy, especially for rare transitions.

Contribution

The paper introduces RECAP, a novel framework that reconstructs long-tail transitions using global transitivity and user revisit evidence, advancing transition-level generalization in mobility prediction.

Findings

RECAP improves overall prediction accuracy across multiple datasets.

Significant gains are observed on tail transition predictions.

The approach effectively reduces transition-level sparsity issues.

Abstract

Human mobility prediction forecasts a user's next Point of Interest (POI) from historical trajectories, supporting applications from recommendation to urban planning. Recent studies have recognized the problem with long-tail POIs in human mobility prediction, which are POIs with few visit records, making new visits to such POIs difficult to predict. Our analysis shows that many predictions fail even for visits to popular POIs. The underlying cause is often transition-level sparsity: the corresponding source-destination transition appears rarely, or never appears, in the training set. We therefore argue that a core bottleneck in human mobility prediction lies in transition-level long-tail generalization. We formulate this problem as compositional generalization and propose a tRansition rEconstruction framework for Compositional generAlization in next-POI prediction (RECAP). RECAP reconstructs long-tail transitions from two generalizable signals: multi-hop transitivity in the global transition graph and revisit evidence from a user's historical trajectory. It further uses warm-transition holdout training to discourage memorization of frequent transitions and encourage generalization from transferable signals. Experiments on multiple real-world datasets show that RECAP consistently improves prediction accuracy, with clear gains on tail transitions.