# Traffic Prediction with Transfer Learning: A Mutual Information-based Approach

arXiv: https://arxiv.org/abs/2303.07184 · HTML: https://mlsanity.com/paper/2303.07184/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 74 references that are in the map.
- First posted on arXiv 13 Mar 2023.

## Builds on (most cited first, 16 of 16)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction](https://mlsanity.com/paper/1811.05320/) (2018)
- [Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction](https://mlsanity.com/paper/1610.00081/) (2016)
- [AdaRNN: Adaptive Learning and Forecasting of Time Series](https://mlsanity.com/paper/2108.04443/) (2021)
- [An Empirical Study of Graph Contrastive Learning](https://mlsanity.com/paper/2109.01116/) (2021)
- [DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction](https://mlsanity.com/paper/2108.09091/) (2021)
- [Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction](https://mlsanity.com/paper/1901.08518/) (2019)
- [Transfer Learning with Graph Neural Networks for Short-Term Highway Traffic Forecasting](https://mlsanity.com/paper/2004.08038/) (2020)
- [Deep Learning for Road Traffic Forecasting: Does it Make a Difference?](https://mlsanity.com/paper/2012.02260/) (2020)
- [Dynamic Origin-Destination Matrix Prediction with Line Graph Neural Networks and Kalman Filter](https://mlsanity.com/paper/1905.00406/) (2019)
- [Smart City Development with Urban Transfer Learning](https://mlsanity.com/paper/1808.01552/) (2018)

## Built on by (most cited first, 6 of 6)

- [Urban traffic analysis and forecasting through shared Koopman eigenmodes](https://mlsanity.com/paper/2409.04728/) (2024)
- [Domain Adaptation Framework for Turning Movement Count Estimation with Limited Data](https://mlsanity.com/paper/2503.20113/) (2025)
- [Multi-Agent Based Transfer Learning for Data-Driven Air Traffic Applications](https://mlsanity.com/paper/2401.14421/) (2024)
- [Geographically-aware Transformer-based Traffic Forecasting for Urban Motorway Digital Twins](https://mlsanity.com/paper/2602.05983/) (2026)
- [Neural Architecture Search for Traffic Prediction: A Survey of Methods, Challenges, and Future Directions](https://mlsanity.com/paper/2607.26467/) (2026)
- [Learning to Transfer Across Modes: Towards Unified Urban Mobility Forecasting](https://mlsanity.com/paper/2608.28273/) (2026)

## Abstract (arXiv)

In modern traffic management, one of the most essential yet challenging tasks is accurately and timely predicting traffic. It has been well investigated and examined that deep learning-based Spatio-temporal models have an edge when exploiting Spatio-temporal relationships in traffic data. Typically, data-driven models require vast volumes of data, but gathering data in small cities can be difficult owing to constraints such as equipment deployment and maintenance costs. To resolve this problem, we propose TrafficTL, a cross-city traffic prediction approach that uses big data from other cities to aid data-scarce cities in traffic prediction. Utilizing a periodicity-based transfer paradigm, it identifies data similarity and reduces negative transfer caused by the disparity between two data distributions from distant cities. In addition, the suggested method employs graph reconstruction techniques to rectify defects in data from small data cities. TrafficTL is evaluated by comprehensive case studies on three real-world datasets and outperforms the state-of-the-art baseline by around 8 to 25 percent.