MobiCLR: Mobility Time Series Contrastive Learning for Urban Region Representations

2025-02-05

AI Summary

This work addresses urban regional representation learning for socioeconomic attribute prediction, focusing on modeling the temporal dynamics and fine-grained semantics embedded in human mobility patterns. We propose a dual-stream contrastive representation learning framework that jointly leverages instance-level contrastive learning and flow-specific regularization—marking the first effort to explicitly disentangle inflow and outflow temporal patterns, thereby enhancing embedding discriminability and interpretability. By aligning dual-stream features and incorporating temporal embeddings, the framework yields semantically rich, time-sensitive regional representations under self-supervision. Empirical evaluation across Chicago, New York City, and Washington, D.C., demonstrates consistent and statistically significant improvements over state-of-the-art methods in predicting income, educational attainment, and social vulnerability indices.

Technology Category

• Machine Learning: Representation Learning
• Computer Vision: Representation Learning for Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Recently, learning effective representations of urban regions has gained significant attention as a key approach to understanding urban dynamics and advancing smarter cities. Existing approaches have demonstrated the potential of leveraging mobility data to generate latent representations, providing valuable insights into the intrinsic characteristics of urban areas. However, incorporating the temporal dynamics and detailed semantics inherent in human mobility patterns remains underexplored. To address this gap, we propose a novel urban region representation learning model, Mobility Time Series Contrastive Learning for Urban Region Representations (MobiCLR), designed to capture semantically meaningful embeddings from inflow and outflow mobility patterns. MobiCLR uses contrastive learning to enhance the discriminative power of its representations, applying an instance-wise contrastive loss to capture distinct flow-specific characteristics. Additionally, we develop a regularizer to align output features with these flow-specific representations, enabling a more comprehensive understanding of mobility dynamics. To validate our model, we conduct extensive experiments in Chicago, New York, and Washington, D.C. to predict income, educational attainment, and social vulnerability. The results demonstrate that our model outperforms state-of-the-art models.

Problem

• Learn urban region representations
• Capture mobility temporal dynamics
• Predict socio-economic indicators

Innovation

• Contrastive learning captures mobility dynamics
• Regularizer aligns features with flow specifics
• MobiCLR outperforms in urban representation tasks