Neural Architecture Search for Traffic Prediction: A Survey of Methods, Challenges, and Future Directions

2026-07-29

AI Summary

Existing traffic forecasting models rely heavily on manually designed architectures, exhibiting limited generalization and strong dependence on expert knowledge. This work presents a systematic survey of neural architecture search (NAS) for spatiotemporal traffic prediction, offering the first comprehensive review of search space design tailored to graph convolutional networks, recurrent architectures, and Transformers. The surveyed methods are organized and analyzed according to three dominant NAS strategies: gradient-based optimization, evolutionary algorithms, and weight-sharing one-shot approaches. The study identifies key limitations in current approaches concerning the trade-off between efficiency and performance, cross-city generalization, and dynamic graph modeling. Building on these insights, it proposes a theoretical framework and outlines promising future directions toward efficient and transferable automated architecture design for traffic forecasting.

Abstract

Traffic prediction is a core task in intelligent transportation systems, supporting applications such as adaptive signal control, route guidance, and ride-hailing dispatch. Deep learning models, including graph convolutional networks, recurrent networks, and Transformers, achieve strong results on standard benchmarks, but their architectures are designed by hand, requiring significant expert effort and producing models that often generalize poorly across cities and datasets. Neural Architecture Search (NAS) offers a systematic alternative to manual design. It automates the search over candidate architectures of deep learning models, finding designs that match the spatial-temporal structure of traffic data without manual trial and error. This survey reviews NAS methods applied to traffic prediction, organized by search strategy: gradient-based methods, evolutionary methods, and one-shot weight-sharing methods. For each category, we analyze how the search space is designed to cover spatial and temporal traffic operators, and how the search strategy balances cost against architecture quality. We also discuss open challenges, computational scalability to large road networks, manual search space design, cross-city generalization, dynamic graph structure, and the open question of NAS for spatial-temporal foundation models, and identify directions for future research.

Problem

• traffic prediction
• neural architecture search
• generalization
• manual architecture design
• spatial-temporal modeling

Innovation

• Neural Architecture Search
• Traffic Prediction
• Spatio-Temporal Modeling
• Automated Machine Learning
• Intelligent Transportation Systems