Online Test-Time Adaptation of Spatial-Temporal Traffic Flow Forecasting

• URL: http://arxiv.org/abs/2401.04148v1
• Date: Mon, 8 Jan 2024 12:04:39 GMT
• Title: Online Test-Time Adaptation of Spatial-Temporal Traffic Flow Forecasting
• Authors: Pengxin Guo, Pengrong Jin, Ziyue Li, Lei Bai, and Yu Zhang
• Abstract summary: This paper conducts the first study of the online test-time adaptation techniques for spatial-temporal traffic flow forecasting problems. We propose an Adaptive Double Correction by Series Decomposition (ADCSD) method, which first decomposes the output of the trained model into seasonal and trend-cyclical parts. In the proposed ADCSD method, instead of fine-tuning the whole trained model during the testing phase, a lite network is attached after the trained model, and only the lite network is fine-tuned in the testing process each time a data entry is observed.
• Score: 13.770733370640565
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate spatial-temporal traffic flow forecasting is crucial in aiding traffic managers in implementing control measures and assisting drivers in selecting optimal travel routes. Traditional deep-learning based methods for traffic flow forecasting typically rely on historical data to train their models, which are then used to make predictions on future data. However, the performance of the trained model usually degrades due to the temporal drift between the historical and future data. To make the model trained on historical data better adapt to future data in a fully online manner, this paper conducts the first study of the online test-time adaptation techniques for spatial-temporal traffic flow forecasting problems. To this end, we propose an Adaptive Double Correction by Series Decomposition (ADCSD) method, which first decomposes the output of the trained model into seasonal and trend-cyclical parts and then corrects them by two separate modules during the testing phase using the latest observed data entry by entry. In the proposed ADCSD method, instead of fine-tuning the whole trained model during the testing phase, a lite network is attached after the trained model, and only the lite network is fine-tuned in the testing process each time a data entry is observed. Moreover, to satisfy that different time series variables may have different levels of temporal drift, two adaptive vectors are adopted to provide different weights for different time series variables. Extensive experiments on four real-world traffic flow forecasting datasets demonstrate the effectiveness of the proposed ADCSD method. The code is available at https://github.com/Pengxin-Guo/ADCSD.

Related papers

• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• Pre-training on Synthetic Driving Data for Trajectory Prediction [61.520225216107306]
  We propose a pipeline-level solution to mitigate the issue of data scarcity in trajectory forecasting. We adopt HD map augmentation and trajectory synthesis for generating driving data, and then we learn representations by pre-training on them. We conduct extensive experiments to demonstrate the effectiveness of our data expansion and pre-training strategies.
  arXiv  Detail & Related papers  (2023-09-18T19:49:22Z)
• Online Evolutionary Neural Architecture Search for Multivariate Non-Stationary Time Series Forecasting [72.89994745876086]
  This work presents the Online Neuro-Evolution-based Neural Architecture Search (ONE-NAS) algorithm. ONE-NAS is a novel neural architecture search method capable of automatically designing and dynamically training recurrent neural networks (RNNs) for online forecasting tasks. Results demonstrate that ONE-NAS outperforms traditional statistical time series forecasting methods.
  arXiv  Detail & Related papers  (2023-02-20T22:25:47Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• Learning spatiotemporal features from incomplete data for traffic flow prediction using hybrid deep neural networks [0.28675177318965034]
  This study focuses on hybrid deep neural networks to predict traffic flow in the California Freeway Performance Measurement System (PeMS) with missing values. Various architecture configurations with series and parallel connections are considered based on RNNs and CNNs. A comprehensive analysis performed on two different datasets from PeMS indicates that the proposed series-parallel hybrid network with the mean imputation technique achieves the lowest error in predicting the traffic flow.
  arXiv  Detail & Related papers  (2022-04-21T15:57:08Z)
• POLA: Online Time Series Prediction by Adaptive Learning Rates [4.105553918089042]
  We propose POLA to automatically regulate the learning rate of recurrent neural network models to adapt to changing time series patterns across time. POLA demonstrates overall comparable or better predictive performance over other online prediction methods.
  arXiv  Detail & Related papers  (2021-02-17T17:56:12Z)
• SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction [72.37440317774556]
  We propose advances that address two key challenges in future trajectory prediction. multimodality in both training data and predictions and constant time inference regardless of number of agents.
  arXiv  Detail & Related papers  (2020-07-26T08:17:10Z)
• Traffic congestion anomaly detection and prediction using deep learning [6.370406399003785]
  Congestion prediction is a major priority for traffic management centres around the world to ensure timely incident response handling. The increasing amounts of generated traffic data have been used to train machine learning predictors for traffic, but this is a challenging task due to inter-dependencies of traffic flow both in time and space. We show that our deep learning models consistently outperform traditional methods, and we conduct a comparative analysis of the optimal time horizon of historical data required to predict traffic flow at different time points in the future.
  arXiv  Detail & Related papers  (2020-06-23T08:49:46Z)
• Short-Term Traffic Forecasting Using High-Resolution Traffic Data [2.0625936401496237]
  This paper develops a data-driven toolkit for traffic forecasting using high-resolution (a.k.a. event-based) traffic data. The proposed methods are verified using high-resolution data obtained from a real-world traffic network in Abu Dhabi, UAE.
  arXiv  Detail & Related papers  (2020-06-22T14:26:19Z)
• Tracking Performance of Online Stochastic Learners [57.14673504239551]
  Online algorithms are popular in large-scale learning settings due to their ability to compute updates on the fly, without the need to store and process data in large batches. When a constant step-size is used, these algorithms also have the ability to adapt to drifts in problem parameters, such as data or model properties, and track the optimal solution with reasonable accuracy. We establish a link between steady-state performance derived under stationarity assumptions and the tracking performance of online learners under random walk models.
  arXiv  Detail & Related papers  (2020-04-04T14:16:27Z)
• New Perspectives on the Use of Online Learning for Congestion Level Prediction over Traffic Data [6.664111208927475]
  This work focuses on classification over time series data. When a time series is generated by non-stationary phenomena, the pattern relating the series with the class to be predicted may evolve over time. Online learning methods incrementally learn from new data samples arriving over time, and accommodate eventual changes along the data stream.
  arXiv  Detail & Related papers  (2020-03-27T09:44:57Z)

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.