mlsanityData to 7 Oct 2026

Learning to Transfer for Traffic Forecasting via Multi-task Learning

arXiv 2111.15542 ↗First posted 27 Nov 2021cs.LG cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have demonstrated superior performance in short-term traffic forecasting. However, most existing traffic forecasting systems assume that the training and testing data are drawn from the same underlying distribution, which limits their practical applicability. The NeurIPS 2021 Traffic4cast challenge is the first of its kind dedicated to benchmarking the robustness of traffic forecasting models towards domain shifts in space and time. This technical report describes our solution to this challenge. In particular, we present a multi-task learning framework for temporal and spatio-temporal domain adaptation of traffic forecasting models. Experimental results demonstrate that our multi-task learning approach achieves strong empirical performance, outperforming a number of baseline domain adaptation methods, while remaining highly efficient. The source code for this technical report is available at https://github.com/YichaoLu/Traffic4cast2021.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 32 of its 65 references that are in the map. First posted on arXiv 27 Nov 2021.

Builds on

32 of 65 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  8. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  9. 2018Group Normalizationcited by 1,514
  10. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  11. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  12. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
20 more
  1. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  2. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  3. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  4. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 433
  5. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 399
  6. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  7. 2016Domain Separation Networkscited by 317
  8. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 285
  9. 2017Deep Learning for Precipitation Nowcasting: A Benchmark and A New Modelcited by 180
  10. 2016Correlation Alignment for Unsupervised Domain Adaptationcited by 146
  11. 2018PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learningcited by 122
  12. 2016Clockwork Convnets for Video Semantic Segmentationcited by 55
  13. 2014Domain Adaptive Neural Networks for Object Recognitioncited by 51
  14. 2017Domain-adversarial neural networks to address the appearance variability of histopathology imagescited by 41
  15. 2014A Unified Perspective on Multi-Domain and Multi-Task Learningcited by 33
  16. 2020Multi-task learning for natural language processing in the 2020s: where are we going?cited by 27
  17. 2015DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detectioncited by 24
  18. 2019CrevNet: Conditionally Reversible Video Predictioncited by 15
  19. 2021Multi-task Learning by Leveraging the Semantic Informationcited by 5
  20. 2019Learning Effective Visual Relationship Detector on 1 GPUcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 2; 2024: 1; 2025: 0; 2026: 1.

7 papers.

  1. 2022Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Citiescited by 38
  2. 2022Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processescited by 15
  3. 2024MobilityDL: A Review of Deep Learning From Trajectory Datacited by 6
  4. 2022A Graph-based U-Net Model for Predicting Traffic in unseen Citiescited by 4
  5. 2023An Efficient Two-stage Gradient Boosting Framework for Short-term Traffic State Estimationcited by 1
  6. 2023Uncertainty Quantification for Image-based Traffic Prediction across Citiescited by 1
  7. 2026A Road-Conditioned Traffic Movie Prediction Network with Spatiotemporal and Structure-Consistent Learningcited by 0