# Traffic Forecasting on New Roads Using Spatial Contrastive Pre-Training (SCPT)

arXiv: https://arxiv.org/abs/2305.05237 · HTML: https://mlsanity.com/paper/2305.05237/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 63 references that are in the map.
- First posted on arXiv 9 May 2023.

## Builds on (most cited first, 30 of 35)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks](https://mlsanity.com/paper/2005.11650/) (2020)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [R-Drop: Regularized Dropout for Neural Networks](https://mlsanity.com/paper/2106.14448/) (2021)
- [Discrete Graph Structure Learning for Forecasting Multiple Time Series](https://mlsanity.com/paper/2101.06861/) (2021)
- [Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting](https://mlsanity.com/paper/2206.09112/) (2022)
- [DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction](https://mlsanity.com/paper/2108.09091/) (2021)
- [Spectral Feature Augmentation for Graph Contrastive Learning and Beyond](https://mlsanity.com/paper/2212.01026/) (2022)
- [COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning](https://mlsanity.com/paper/2206.04726/) (2022)
- [When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?](https://mlsanity.com/paper/2108.11873/) (2021)
- [Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement](https://mlsanity.com/paper/2304.11598/) (2023)
- [Contrastive Laplacian Eigenmaps](https://mlsanity.com/paper/2201.05493/) (2022)
- [Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition](https://mlsanity.com/paper/2210.16820/) (2022)
- [Deep Learning for Road Traffic Forecasting: Does it Make a Difference?](https://mlsanity.com/paper/2012.02260/) (2020)
- [Uncertainty-DTW for Time Series and Sequences](https://mlsanity.com/paper/2211.00005/) (2022)
- [Graph-Partitioning-Based Diffusion Convolutional Recurrent Neural Network for Large-Scale Traffic Forecasting](https://mlsanity.com/paper/1909.11197/) (2019)
- [Graph Markov Network for Traffic Forecasting with Missing Data](https://mlsanity.com/paper/1912.05457/) (2019)
- [Second-order Democratic Aggregation](https://mlsanity.com/paper/1808.07503/) (2018)
- [3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na"ive](https://mlsanity.com/paper/2112.12668/) (2021)

## Built on by (most cited first, 11 of 11)

- [Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey](https://mlsanity.com/paper/2503.13502/) (2025)
- [XXLTraffic: Expanding and Extremely Long Traffic forecasting beyond test adaptation](https://mlsanity.com/paper/2406.12693/) (2024)
- [Inductive Graph Few-shot Class Incremental Learning](https://mlsanity.com/paper/2411.06634/) (2024)
- [Navigating Out-of-Distribution Electricity Load Forecasting during COVID-19: Benchmarking energy load forecasting models without and with continual learning](https://mlsanity.com/paper/2309.04296/) (2023)
- [Enhancing Spatio-temporal Quantile Forecasting with Curriculum Learning: Lessons Learned](https://mlsanity.com/paper/2406.12709/) (2024)
- [On the Regularization of Learnable Embeddings for Time Series Forecasting](https://mlsanity.com/paper/2410.14630/) (2024)
- [Structure-preserving contrastive learning for spatial time series](https://mlsanity.com/paper/2502.06380/) (2025)
- [From XXLTraffic to EvoXXLTraffic: Scaling Traffic Forecasting to Sensor-Evolving Networks](https://mlsanity.com/paper/2605.29768/) (2026)
- [A Gap in Time: The Challenge of Processing Heterogeneous IoT Data in Digitalized Buildings](https://mlsanity.com/paper/2405.14267/) (2024)
- [Embedding spatial context in urban traffic forecasting with contrastive pre-training](https://mlsanity.com/paper/2503.14980/) (2025)
- [A Road-Conditioned Traffic Movie Prediction Network with Spatiotemporal and Structure-Consistent Learning](https://mlsanity.com/paper/2605.27884/) (2026)

## Abstract (arXiv)

New roads are being constructed all the time. However, the capabilities of previous deep forecasting models to generalize to new roads not seen in the training data (unseen roads) are rarely explored. In this paper, we introduce a novel setup called a spatio-temporal (ST) split to evaluate the models' capabilities to generalize to unseen roads. In this setup, the models are trained on data from a sample of roads, but tested on roads not seen in the training data. Moreover, we also present a novel framework called Spatial Contrastive Pre-Training (SCPT) where we introduce a spatial encoder module to extract latent features from unseen roads during inference time. This spatial encoder is pre-trained using contrastive learning. During inference, the spatial encoder only requires two days of traffic data on the new roads and does not require any re-training. We also show that the output from the spatial encoder can be used effectively to infer latent node embeddings on unseen roads during inference time. The SCPT framework also incorporates a new layer, named the spatially gated addition (SGA) layer, to effectively combine the latent features from the output of the spatial encoder to existing backbones. Additionally, since there is limited data on the unseen roads, we argue that it is better to decouple traffic signals to trivial-to-capture periodic signals and difficult-to-capture Markovian signals, and for the spatial encoder to only learn the Markovian signals. Finally, we empirically evaluated SCPT using the ST split setup on four real-world datasets. The results showed that adding SCPT to a backbone consistently improves forecasting performance on unseen roads. More importantly, the improvements are greater when forecasting further into the future. The codes are available on GitHub: https://github.com/cruiseresearchgroup/forecasting-on-new-roads .