DSETA: A Dual-Stage Continual Learning Framework for Travel Time Prediction in Dynamic Traffic Environments

• URL: http://arxiv.org/abs/2608.00402v1
• Date: Sat, 01 Aug 2026 02:55:14 GMT
• Title: DSETA: A Dual-Stage Continual Learning Framework for Travel Time Prediction in Dynamic Traffic Environments
• Abstract summary: DSETA is an incrementally updated Dual-Stage ETA prediction framework.<n>We first design the textitintra-day learning stage, which relies entirely on real-time data.<n>Next, we develop the textitinter-day learning stage, which leverages aggregated historical data from a short time window.<n>We validate DSETA's effectiveness and robustness through extensive offline and online experiments conducted on real-world datasets from DiDi's platform.
• Score: 11.671189656375264
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Estimated Time of Arrival (ETA) prediction is a core component of intelligent transportation systems. As traffic congestion patterns become increasingly dynamic in large cities, maintaining high prediction accuracy poses a major challenge for ride-hailing platforms. Existing methods either fail to adapt to irregular traffic patterns and sudden congestion, or suffer from new distributions without disentangling long-term trends from short-term fluctuations, thereby degrading model performance in real-world scenarios. To address this challenge, we propose DSETA, an incrementally updated Dual-Stage ETA prediction framework. Specifically, the continual learning process is divided into \textit{inter-day} and \textit{intra-day} stages. We first design the \textit{intra-day} learning stage, which relies entirely on real-time data to enable dynamic adaptation to short-term traffic patterns caused by events like holidays or accidents. Next, we develop the \textit{inter-day} learning stage, which leverages aggregated historical data from a short time window to capture knowledge of long-term distribution shifts, such as seasonal trends and traffic network evolution. Subsequently, to prevent catastrophic forgetting and preserve knowledge of regular patterns, we explore a \textit{Historical Traffic Knowledge Consolidation} module. Finally, we validate DSETA's effectiveness and robustness through extensive offline and online experiments conducted on real-world datasets from DiDi's platform. Online A/B tests across three major cities including Beijing, Wuhan, and Xi'an consistently demonstrated performance gains, achieving MAE reductions of 6.62\%, 0.73\%, and 2.40\% respectively. This framework has been successfully deployed in DiDi's production environment, processing hundreds of millions of daily requests and validating its strong performance in industrial applications.

Related papers

• LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling [74.94985663101906]
  We present LeapTS, a novel framework that reformulates time series forecasting as a dynamic scheduling process over the prediction horizon.<n>We show that LeapTS improves overall forecasting performance by at least 7.4% while achieving a 2.6$times$ to 5.3$times$ inference speedup over representative Transformer-based models.
  arXiv  Detail & Related papers  (2026-05-11T09:54:02Z)
• Learning from Yesterday's Error: An Efficient Online Learning Method for Traffic Demand Prediction [6.104967994062357]
  FORESEE (Forecasting Online with Residual Smoothing and Ensemble Experts) is a lightweight online adaptation framework that is accurate, robust, and efficient.<n>It corrects today's forecast in each region using yesterday's prediction error, through exponential smoothing guided by a mixture-of-experts mechanism.<n>Experiments on seven real-world datasets with backbone models demonstrate that FORESEE consistently improves prediction accuracy, maintains robustness even when distribution shifts are minimal.
  arXiv  Detail & Related papers  (2026-02-25T10:19:39Z)
• TEAM: Topological Evolution-aware Framework for Traffic Forecasting--Extended Version [24.544665297938437]
  Topological Evolution-aware Framework (TEAM) for traffic forecasting incorporates convolution and attention.<n>TEAM is capable of much lower re-training costs than existing methods are without jeopardizing forecasting accuracy.
  arXiv  Detail & Related papers  (2024-10-24T22:50:21Z)
• DST-TransitNet: A Dynamic Spatio-Temporal Deep Learning Model for Scalable and Efficient Network-Wide Prediction of Station-Level Transit Ridership [12.6020349733674]
  This paper introduces DST-TransitNet, a hybrid Deep Learning model for system-wide ridership prediction. It is tested on Bogota's BRT system data, with three distinct social scenarios. It outperforms state-of-the-art models in precision, efficiency and robustness.
  arXiv  Detail & Related papers  (2024-10-19T06:59:39Z)
• A Practitioner's Guide to Continual Multimodal Pretraining [83.63894495064855]
  Multimodal foundation models serve numerous applications at the intersection of vision and language.<n>To keep models updated, research into continual pretraining mainly explores scenarios with either infrequent, indiscriminate updates on large-scale new data, or frequent, sample-level updates.<n>We introduce FoMo-in-Flux, a continual multimodal pretraining benchmark with realistic compute constraints and practical deployment requirements.
  arXiv  Detail & Related papers  (2024-08-26T17:59:01Z)
• Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
  Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models. Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML) We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
  arXiv  Detail & Related papers  (2024-07-18T15:44:23Z)
• XXLTraffic: Expanding and Extremely Long Traffic forecasting beyond test adaptation [3.7509821052818118]
  XXLTraffic is largest available public traffic dataset with the longest timespan from Los Angeles, USA, and New South Wales, Australia.<n>Our dataset supplements existing-temporal data resources and leads to new research directions in this domain.
  arXiv  Detail & Related papers  (2024-06-18T15:06:22Z)
• PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction [78.05103666987655]
  spatial-temporal Graph Neural Network (GNN) models have emerged as one of the most promising methods to solve this problem. We propose a novel propagation delay-aware dynamic long-range transFormer, namely PDFormer, for accurate traffic flow prediction. Our method can not only achieve state-of-the-art performance but also exhibit competitive computational efficiency.
  arXiv  Detail & Related papers  (2023-01-19T08:42:40Z)
• D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights [68.76631399516823]
  We present a trajectory prediction approach with respect to traffic lights, D2-TPred, using a spatial dynamic interaction graph (SDG) and a behavior dependency graph (BDG) Our experimental results show that our model achieves more than 20.45% and 20.78% in terms of ADE and FDE, respectively, on VTP-TL.
  arXiv  Detail & Related papers  (2022-07-21T10:19:07Z)
• Continuous-Time and Multi-Level Graph Representation Learning for Origin-Destination Demand Prediction [52.0977259978343]
  This paper proposes a Continuous-time and Multi-level dynamic graph representation learning method for Origin-Destination demand prediction (CMOD) The state vectors keep historical transaction information and are continuously updated according to the most recently happened transactions. Experiments are conducted on two real-world datasets from Beijing Subway and New York Taxi, and the results demonstrate the superiority of our model against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-06-30T03:37:50Z)
• Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms [57.21078336887961]
  Large ride-hailing platforms, such as DiDi, Uber and Lyft, connect tens of thousands of vehicles in a city to millions of ride demands throughout the day. We propose a unified value-based dynamic learning framework (V1D3) for tackling both tasks.
  arXiv  Detail & Related papers  (2021-05-18T19:22:24Z)
• Progressive Growing of Neural ODEs [7.558546277131641]
  We propose a progressive learning paradigm of NODEs for long-term time series forecasting. Specifically, following the principle of curriculum learning, we gradually increase the complexity of data and network capacity as training progresses. Our experiments with both synthetic data and real traffic data (PeMS Bay Area traffic data) show that our training methodology consistently improves the performance of vanilla NODEs by over 64%.
  arXiv  Detail & Related papers  (2020-03-08T01:15:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.