# Joint Demand Prediction for Multimodal Systems: A Multi-task Multi-relational Spatiotemporal Graph Neural Network Approach

arXiv: https://arxiv.org/abs/2112.08078 · HTML: https://mlsanity.com/paper/2112.08078/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 15 Dec 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [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)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [Graph Neural Network for Traffic Forecasting: A Survey](https://mlsanity.com/paper/2101.11174/) (2021)
- [Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction](https://mlsanity.com/paper/1802.08714/) (2018)
- [A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources](https://mlsanity.com/paper/2011.14867/) (2020)
- [Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: A Spatio-Temporal Deep Learning Approach](https://mlsanity.com/paper/1706.06279/) (2017)
- [Joint predictions of multi-modal ride-hailing demands: a deep multi-task multigraph learning-based approach](https://mlsanity.com/paper/2011.05602/) (2020)
- [Dynamic Spatiotemporal Graph Convolutional Neural Networks for Traffic Data Imputation with Complex Missing Patterns](https://mlsanity.com/paper/2109.08357/) (2021)

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

- [Exploring Large Language Models for Human Mobility Prediction under Public Events](https://mlsanity.com/paper/2311.17351/) (2023)
- [Causal conditional hidden Markov model for multimodal traffic prediction](https://mlsanity.com/paper/2301.08249/) (2023)
- [UQGNN: Uncertainty Quantification of Graph Neural Networks for Multivariate Spatiotemporal Prediction](https://mlsanity.com/paper/2508.08551/) (2025)
- [Cross-Mode Knowledge Adaptation for Bike Sharing Demand Prediction using Domain-Adversarial Graph Neural Networks](https://mlsanity.com/paper/2211.08903/) (2022)
- [Short-term passenger flow prediction for multi-traffic modes: A Transformer and residual network based multi-task learning method](https://mlsanity.com/paper/2203.00422/) (2022)
- [Bike Sharing Demand Prediction based on Knowledge Sharing across Modes: A Graph-based Deep Learning Approach](https://mlsanity.com/paper/2203.10961/) (2022)
- [Transfer learning for cross-modal demand prediction of bike-share and public transit](https://mlsanity.com/paper/2203.09279/) (2022)
- [Multimodal joint prediction of traffic spatial-temporal data with graph sparse attention mechanism and bidirectional temporal convolutional network](https://mlsanity.com/paper/2412.19842/) (2024)
- [Edge Ranking of Graphs in Transportation Networks using a Graph Neural Network (GNN)](https://mlsanity.com/paper/2303.17485/) (2023)
- [Virtual Smart Metering in District Heating Networks via Heterogeneous Spatial-Temporal Graph Neural Networks](https://mlsanity.com/paper/2604.10166/) (2026)
- [SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark](https://mlsanity.com/paper/2610.13730/) (2026)

## Abstract (arXiv)

Dynamic demand prediction is crucial for the efficient operation and management of urban transportation systems. Extensive research has been conducted on single-mode demand prediction, ignoring the fact that the demands for different transportation modes can be correlated with each other. Despite some recent efforts, existing approaches to multimodal demand prediction are generally not flexible enough to account for multiplex networks with diverse spatial units and heterogeneous spatiotemporal correlations across different modes. To tackle these issues, this study proposes a multi-relational spatiotemporal graph neural network (ST-MRGNN) for multimodal demand prediction. Specifically, the spatial dependencies across modes are encoded with multiple intra- and inter-modal relation graphs. A multi-relational graph neural network (MRGNN) is introduced to capture cross-mode heterogeneous spatial dependencies, consisting of generalized graph convolution networks to learn the message passing mechanisms within relation graphs and an attention-based aggregation module to summarize different relations. We further integrate MRGNNs with temporal gated convolution layers to jointly model heterogeneous spatiotemporal correlations. Extensive experiments are conducted using real-world subway and ride-hailing datasets from New York City, and the results verify the improved performance of our proposed approach over existing methods across modes. The improvement is particularly large for demand-sparse locations. Further analysis of the attention mechanisms of ST-MRGNN also demonstrates its good interpretability for understanding cross-mode interactions.