# Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Prediction

arXiv: https://arxiv.org/abs/2406.12923 · HTML: https://mlsanity.com/paper/2406.12923/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts.
- Builds on 26 of its 64 references that are in the map.
- First posted on arXiv 14 Jun 2024.

## Placed in

- Mixture-of-experts / [MoE for time series and graphs](https://mlsanity.com/moe/moe-for-time-series-and-graphs/)

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [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)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts](https://mlsanity.com/paper/2206.02770/) (2022)
- [Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks](https://mlsanity.com/paper/2112.14936/) (2021)
- [Efficient Large Scale Language Modeling with Mixtures of Experts](https://mlsanity.com/paper/2112.10684/) (2021)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)
- [Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2208.05233/) (2022)
- [A Review of Sparse Expert Models in Deep Learning](https://mlsanity.com/paper/2209.01667/) (2022)
- [Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling](https://mlsanity.com/paper/2304.02806/) (2023)
- [RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression](https://mlsanity.com/paper/2205.15236/) (2022)
- [Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models](https://mlsanity.com/paper/2210.02447/) (2022)
- [MugRep: A Multi-Task Hierarchical Graph Representation Learning Framework for Real Estate Appraisal](https://mlsanity.com/paper/2107.05180/) (2021)
- [DeepTransport: Learning Spatial-Temporal Dependency for Traffic Condition Forecasting](https://mlsanity.com/paper/1709.09585/) (2017)
- [Applications of deep learning in traffic congestion detection, prediction and alleviation: A survey](https://mlsanity.com/paper/2102.09759/) (2021)
- [Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Prediction](https://mlsanity.com/paper/2311.08635/) (2023)
- [PCNN: Deep Convolutional Networks for Short-term Traffic Congestion Prediction](https://mlsanity.com/paper/2003.07033/) (2020)
- [Polestar: An Intelligent, Efficient and National-Wide Public Transportation Routing Engine](https://mlsanity.com/paper/2007.07195/) (2020)
- [Mixture of Weak & Strong Experts on Graphs](https://mlsanity.com/paper/2311.05185/) (2023)

## Built on by (most cited first, 7 of 7)

- [ViTE: Virtual Graph Trajectory Expert Router for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2511.12214/) (2025)
- [Spatial-Temporal Mixture-of-Graph-Experts for Multi-Type Crime Prediction](https://mlsanity.com/paper/2409.15764/) (2024)
- [Alleviating Performance Disparity in Adversarial Spatiotemporal Graph Learning Under Zero-Inflated Distribution](https://mlsanity.com/paper/2504.00721/) (2025)
- [OmniPlan: An Adaptive Framework for Timely and Near-Optimal Network Planning Optimization](https://mlsanity.com/paper/2606.18105/) (2026)
- [HiMoE: Heterogeneity-Informed Mixture-of-Experts for Fair Spatial-Temporal Forecasting](https://mlsanity.com/paper/2412.00316/) (2024)
- [MixTTE: Multi-Level Mixture-of-Experts for Scalable and Adaptive Travel Time Estimation](https://mlsanity.com/paper/2601.02943/) (2026)
- [A Multi-Resolution Multi-Domain Pre-Training Framework for Universal Traffic Forecasting](https://mlsanity.com/paper/2609.13878/) (2026)

## Abstract (arXiv)

Rapid urbanization has significantly escalated traffic congestion, underscoring the need for advanced congestion prediction services to bolster intelligent transportation systems. As one of the world's largest ride-hailing platforms, DiDi places great emphasis on the accuracy of congestion prediction to enhance the effectiveness and reliability of their real-time services, such as travel time estimation and route planning. Despite numerous efforts have been made on congestion prediction, most of them fall short in handling heterogeneous and dynamic spatio-temporal dependencies (e.g., periodic and non-periodic congestions), particularly in the presence of noisy and incomplete traffic data. In this paper, we introduce a Congestion Prediction Mixture-of-Experts, CP-MoE, to address the above challenges. We first propose a sparsely-gated Mixture of Adaptive Graph Learners (MAGLs) with congestion-aware inductive biases to improve the model capacity for efficiently capturing complex spatio-temporal dependencies in varying traffic scenarios. Then, we devise two specialized experts to help identify stable trends and periodic patterns within the traffic data, respectively. By cascading these experts with MAGLs, CP-MoE delivers congestion predictions in a more robust and interpretable manner. Furthermore, an ordinal regression strategy is adopted to facilitate effective collaboration among diverse experts. Extensive experiments on real-world datasets demonstrate the superiority of our proposed method compared with state-of-the-art spatio-temporal prediction models. More importantly, CP-MoE has been deployed in DiDi to improve the accuracy and reliability of the travel time estimation system.