UrbanMoE: A Sparse Multi-Modal Mixture-of-Experts Framework for Multi-Task Urban Region Profiling

2026-01-30

AI Summary

This work addresses the limitations of existing urban area profiling methods, which are often confined to single-task prediction and struggle to capture complex interdependencies among multiple indicators, while also lacking a unified multi-task evaluation benchmark. To this end, we establish the first standardized benchmark for multi-task urban area profiling and propose UrbanMoE, a novel framework that introduces, for the first time, a sparse multimodal mixture-of-experts (Sparse MoE) mechanism. UrbanMoE integrates dynamic routing with multimodal feature fusion to enable effective joint multi-task prediction. Extensive experiments on three real-world datasets demonstrate that our approach significantly outperforms current baselines, achieving state-of-the-art performance and confirming its effectiveness and efficiency.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Urban region profiling, the task of characterizing geographical areas, is crucial for urban planning and resource allocation. However, existing research in this domain faces two significant limitations. First, most methods are confined to single-task prediction, failing to capture the interconnected, multi-faceted nature of urban environments where numerous indicators are deeply correlated. Second, the field lacks a standardized experimental benchmark, which severely impedes fair comparison and reproducible progress. To address these challenges, we first establish a comprehensive benchmark for multi-task urban region profiling, featuring multi-modal features and a diverse set of strong baselines to ensure a fair and rigorous evaluation environment. Concurrently, we propose UrbanMoE, the first sparse multi-modal, multi-expert framework specifically architected to solve the multi-task challenge. Leveraging a sparse Mixture-of-Experts architecture, it dynamically routes multi-modal features to specialized sub-networks, enabling the simultaneous prediction of diverse urban indicators. We conduct extensive experiments on three real-world datasets within our benchmark, where UrbanMoE consistently demonstrates superior performance over all baselines. Further in-depth analysis validates the efficacy and efficiency of our approach, setting a new state-of-the-art and providing the community with a valuable tool for future research in urban analytics

Problem

• urban region profiling
• multi-task learning
• multi-modal data
• benchmark
• Mixture-of-Experts

Innovation

• Mixture-of-Experts
• multi-task learning
• urban region profiling
• sparse architecture
• multi-modal fusion