mlsanityData to 7 Oct 2026

MixTTE: Multi-Level Mixture-of-Experts for Scalable and Adaptive Travel Time Estimation

arXiv 2601.02943 ↗First posted 6 Jan 2026cs.LG cs.MAcited by 0

On the map: Mixture-of-experts → MoE for time series and graphs

Abstract (arXiv)

Accurate Travel Time Estimation (TTE) is critical for ride-hailing platforms, where errors directly impact user experience and operational efficiency. While existing production systems excel at holistic route-level dependency modeling, they struggle to capture city-scale traffic dynamics and long-tail scenarios, leading to unreliable predictions in large urban networks. In this paper, we propose model, a scalable and adaptive framework that synergistically integrates link-level modeling with industrial route-level TTE systems. Specifically, we propose a spatio-temporal external attention module to capture global traffic dynamic dependencies across million-scale road networks efficiently. Moreover, we construct a stabilized graph mixture-of-experts network to handle heterogeneous traffic patterns while maintaining inference efficiency. Furthermore, an asynchronous incremental learning strategy is tailored to enable real-time and stable adaptation to dynamic traffic distribution shifts. Experiments on real-world datasets validate MixTTE significantly reduces prediction errors compared to seven baselines. MixTTE has been deployed in DiDi, substantially improving the accuracy and stability of the TTE service.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts. Builds on 28 of its 60 references that are in the map. First posted on arXiv 6 Jan 2026.

Builds on

28 of 60 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts24 Sep
  2. 2024Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Prediction14 Jun
  3. 2024Continual Traffic Forecasting via Mixture of Experts5 Jun
  4. 2024TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts5 Mar
  5. 2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling6 Apr

Other references · 23

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  2. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  3. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  4. 2019Simplifying Graph Convolutional Networkscited by 1,470
  5. 2018Experience Replay for Continual Learningcited by 1,074
  6. 2021Scaling Vision with Sparse Mixture of Expertscited by 740
  7. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
  8. 2022DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scalecited by 400
  9. 2024Transolver: A Fast Transformer Solver for PDEs on General Geometriescited by 299
  10. 2023From Sparse to Soft Mixtures of Expertscited by 245
  11. 2022Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Expertscited by 202
  12. 2022A Review of Sparse Expert Models in Deep Learningcited by 147
11 more
  1. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
  2. 2021Beyond Self-attention: External Attention using Two Linear Layers for Visual Taskscited by 109
  3. 2017Incremental Learning Through Deep Adaptationcited by 108
  4. 2024MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Expertscited by 55
  5. 2018DeepTravel: a Neural Network Based Travel Time Estimation Model with Auxiliary Supervisioncited by 21
  6. 2023Origin-Destination Travel Time Oracle for Map-based Servicescited by 20
  7. 2022DuETA: Traffic Congestion Propagation Pattern Modeling via Efficient Graph Learning for ETA Prediction at Baidu Mapscited by 10
  8. 2024Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecastingcited by 10
  9. 2024TEAM: Topological Evolution-aware Framework for Traffic Forecasting--Extended Versioncited by 10
  10. 2024DutyTTE: Deciphering Uncertainty in Origin-Destination Travel Time Estimationcited by 6
  11. 2024MH-MoE: Multi-Head Mixture-of-Expertscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026A Multi-Resolution Multi-Domain Pre-Training Framework for Universal Traffic Forecasting
  2. 2025Less is More: Strategic Expert Selection Outperforms Ensemble Complexity in Traffic Forecasting
  3. 2026STHMoE: Hypergraph-Enhanced Heterogeneous Dependency Coordination for LLM-Based Urban Traffic Data Forecasting
  4. 2026FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction
  5. 2026GAMMA-Net: Adaptive Long-Horizon Traffic Spatio-Temporal Forecasting Model based on Interleaved Graph Attention and Multi-Axis Mamba
  6. 2024A Time Series is Worth Five Experts: Heterogeneous Mixture of Experts for Traffic Flow Prediction
  7. 2026PHGNet: Prototype-Guided Hypergraph Construction for Heterogeneous Spatiotemporal Forecasting
  8. 2025RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-Hailing