City-Conditioned Memory for Multi-City Traffic and Mobility Forecasting

2025/11/30 by Wenqi Du, Du, Wenzhang
Engineering · Social Sciences · #62M10 #68T07 #90B20 #Advanced Data and IoT Technologies #Computers and Society (cs.CY) #FOS: Computer and information sciences #G.3 #Human Mobility and Location-Based Analysis #I.2.6 #I.5.1 #Machine Learning (cs.LG) #Traffic Prediction and Management Techniques

paper · pdf · doi:10.48550/arxiv.2512.00851

openalex publication_date 2025/11/30 · openalex created_date 2025/12/03 · openalex updated_date 2026/07/28

Abstract

Deploying spatio-temporal forecasting models across many cities is difficult: traffic networks differ in size and topology, data availability can vary by orders of magnitude, and new cities may provide only a short history of logs. Existing deep traffic models are typically trained per city and backbone, creating high maintenance cost and poor transfer to data-scarce cities. We ask whether a single, backbone-agnostic layer can condition on "which city this sequence comes from", improve accuracy in full- and low-data regimes, and support better cross-city adaptation with minimal code changes. We propose CityCond, a light-weight city-conditioned memory layer that augments existing spatio-temporal backbones. CityCond combines a city-ID encoder with an optional shared memory bank (CityMem). Given a city index and backbone hidden states, it produces city-conditioned features fused through gated residual connections. We attach CityCond to five representative backbones (GRU, TCN, Transformer, GNN, STGCN) and evaluate three regimes: full-data, low-data, and cross-city few-shot transfer on METR-LA and PEMS-BAY. We also run auxiliary experiments on SIND, a drone-based multi-agent trajectory dataset from a signalized intersection in Tianjin (we focus on pedestrian tracks). Across more than fourteen model variants and three random seeds, CityCond yields consistent improvements, with the largest gains for high-capacity backbones such as Transformers and STGCNs. CityMem reduces Transformer error by roughly one third in full-data settings and brings substantial gains in low-data and cross-city transfer. On SIND, simple city-ID conditioning modestly improves low-data LSTM performance. CityCond can therefore serve as a reusable design pattern for scalable, multi-city forecasting under realistic data constraints.

Citations

• SIND: A Drone Dataset at Signalized Intersection in China
• Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Graph WaveNet for Deep Spatial-Temporal Graph Modeling
• Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction
• Social GAN: Socially Acceptable Trajectories with Generative Adversarial\n Networks
• A Comprehensive Survey on Graph Neural Networks

Related

• Cross-city Few-Shot Traffic Forecasting via Traffic Pattern Bank
• Multi-scale Traffic Pattern Bank for Cross-city Few-shot Traffic Forecasting
• SSMT: Few-Shot Traffic Forecasting with Single Source Meta-Transfer
• Frequency Enhanced Pre-training for Cross-city Few-shot Traffic Forecasting
• Traffic Prediction with Transfer Learning: A Mutual Information-based Approach