# NodeTrans: A Graph Transfer Learning Approach for Traffic Prediction

arXiv: https://arxiv.org/abs/2207.01301 · HTML: https://mlsanity.com/paper/2207.01301/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 30 references that are in the map.
- First posted on arXiv 4 Jul 2022.

## Builds on (most cited first, 14 of 14)

- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https://mlsanity.com/paper/1911.08415/) (2019)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction](https://mlsanity.com/paper/1610.00081/) (2016)
- [Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting](https://mlsanity.com/paper/2012.09641/) (2020)
- [Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting](https://mlsanity.com/paper/1802.07007/) (2018)
- [Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction](https://mlsanity.com/paper/1901.08518/) (2019)
- [Coupled Layer-wise Graph Convolution for Transportation Demand Prediction](https://mlsanity.com/paper/2012.08080/) (2020)
- [Nearly Optimal Regret for Stochastic Linear Bandits with Heavy-Tailed Payoffs](https://mlsanity.com/paper/2004.13465/) (2020)
- [Cross-City Transfer Learning for Deep Spatio-Temporal Prediction](https://mlsanity.com/paper/1802.00386/) (2018)

## Built on by (most cited first, 5 of 5)

- [Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey](https://mlsanity.com/paper/2303.14483/) (2023)
- [Taming Local Effects in Graph-based Spatiotemporal Forecasting](https://mlsanity.com/paper/2302.04071/) (2023)
- [Graph Deep Learning for Time Series Forecasting](https://mlsanity.com/paper/2310.15978/) (2023)
- [On the Regularization of Learnable Embeddings for Time Series Forecasting](https://mlsanity.com/paper/2410.14630/) (2024)
- [AdaKernel: Learning Adaptive Kernel Parameters for Spatiotemporal Graph Neural Networks](https://mlsanity.com/paper/2606.01283/) (2026)

## Abstract (arXiv)

Recently, deep learning methods have made great progress in traffic prediction, but their performance depends on a large amount of historical data. In reality, we may face the data scarcity issue. In this case, deep learning models fail to obtain satisfactory performance. Transfer learning is a promising approach to solve the data scarcity issue. However, existing transfer learning approaches in traffic prediction are mainly based on regular grid data, which is not suitable for the inherent graph data in the traffic network. Moreover, existing graph-based models can only capture shared traffic patterns in the road network, and how to learn node-specific patterns is also a challenge. In this paper, we propose a novel transfer learning approach to solve the traffic prediction with few data, which can transfer the knowledge learned from a data-rich source domain to a data-scarce target domain. First, a spatial-temporal graph neural network is proposed, which can capture the node-specific spatial-temporal traffic patterns of different road networks. Then, to improve the robustness of transfer, we design a pattern-based transfer strategy, where we leverage a clustering-based mechanism to distill common spatial-temporal patterns in the source domain, and use these knowledge to further improve the prediction performance of the target domain. Experiments on real-world datasets verify the effectiveness of our approach.