SSMT: Few-Shot Traffic Forecasting with Single Source Meta-Transfer

• URL: http://arxiv.org/abs/2410.15589v1
• Date: Mon, 21 Oct 2024 02:17:25 GMT
• Title: SSMT: Few-Shot Traffic Forecasting with Single Source Meta-Transfer
• Authors: Kishor Kumar Bhaumik, Minha Kim, Fahim Faisal Niloy, Amin Ahsan Ali, Simon S. Woo,
• Abstract summary: We introduce Single Source Meta-Transfer Learning (SSMT) which relies only on a single source city for traffic prediction. Our method harnesses this transferred knowledge to enable few-shot traffic forecasting, particularly when the target city possesses limited data. We extend the idea of sinusoidal positional encoding to establish meta-learning tasks by leveraging diverse temporal traffic patterns from the source city.
• Score: 19.768107394061374
• License:
• Abstract: Traffic forecasting in Intelligent Transportation Systems (ITS) is vital for intelligent traffic prediction. Yet, ITS often relies on data from traffic sensors or vehicle devices, where certain cities might not have all those smart devices or enabling infrastructures. Also, recent studies have employed meta-learning to generalize spatial-temporal traffic networks, utilizing data from multiple cities for effective traffic forecasting for data-scarce target cities. However, collecting data from multiple cities can be costly and time-consuming. To tackle this challenge, we introduce Single Source Meta-Transfer Learning (SSMT) which relies only on a single source city for traffic prediction. Our method harnesses this transferred knowledge to enable few-shot traffic forecasting, particularly when the target city possesses limited data. Specifically, we use memory-augmented attention to store the heterogeneous spatial knowledge from the source city and selectively recall them for the data-scarce target city. We extend the idea of sinusoidal positional encoding to establish meta-learning tasks by leveraging diverse temporal traffic patterns from the source city. Moreover, to capture a more generalized representation of the positions we introduced a meta-positional encoding that learns the most optimal representation of the temporal pattern across all the tasks. We experiment on five real-world benchmark datasets to demonstrate that our method outperforms several existing methods in time series traffic prediction.

Related papers

• Strada-LLM: Graph LLM for traffic prediction [62.2015839597764]
  A considerable challenge in traffic prediction lies in handling the diverse data distributions caused by vastly different traffic conditions. We propose a graph-aware LLM for traffic prediction that considers proximal traffic information. We adopt a lightweight approach for efficient domain adaptation when facing new data distributions in few-shot fashion.
  arXiv  Detail & Related papers  (2024-10-28T09:19:29Z)
• Urban traffic analysis and forecasting through shared Koopman eigenmodes [5.207485728774798]
  Predicting traffic flow in data-scarce cities is challenging due to limited historical data. We leverage transfer learning by identifying periodic patterns common to data-rich cities. This method uncovers common eigenmodes (urban heartbeats) in traffic patterns and transfers them to data-scarce cities.
  arXiv  Detail & Related papers  (2024-09-07T06:24:50Z)
• BjTT: A Large-scale Multimodal Dataset for Traffic Prediction [49.93028461584377]
  Traditional traffic prediction methods rely on historical traffic data to predict traffic trends. In this work, we explore how generative models combined with text describing the traffic system can be applied for traffic generation. We propose ChatTraffic, the first diffusion model for text-to-traffic generation.
  arXiv  Detail & Related papers  (2024-03-08T04:19:56Z)
• Cross-city Few-Shot Traffic Forecasting via Traffic Pattern Bank [15.123457772023238]
  We propose a cross-city few-shot traffic forecasting framework via Traffic Pattern Bank (TPB) TPB utilizes a pre-trained traffic patch encoder to project raw traffic data from data-rich cities into high-dimensional space. An adjacency matrix is constructed to guide a downstream spatial-temporal model in forecasting future traffic.
  arXiv  Detail & Related papers  (2023-08-17T13:29:57Z)
• Traffic Prediction with Transfer Learning: A Mutual Information-based Approach [11.444576186559487]
  We propose TrafficTL, a cross-city traffic prediction approach that uses big data from other cities to aid data-scarce cities in traffic prediction. TrafficTL is evaluated by comprehensive case studies on three real-world datasets and outperforms the state-of-the-art baseline by around 8 to 25 percent.
  arXiv  Detail & Related papers  (2023-03-13T15:27:07Z)
• 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)
• Efficient Federated Learning with Spike Neural Networks for Traffic Sign Recognition [70.306089187104]
  We introduce powerful Spike Neural Networks (SNNs) into traffic sign recognition for energy-efficient and fast model training. Numerical results indicate that the proposed federated SNN outperforms traditional federated convolutional neural networks in terms of accuracy, noise immunity, and energy efficiency as well.
  arXiv  Detail & Related papers  (2022-05-28T03:11:48Z)
• Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer [58.6106391721944]
  Cross-city knowledge has shown its promise, where the model learned from data-sufficient cities is leveraged to benefit the learning process of data-scarce cities. We propose a model-agnostic few-shot learning framework for S-temporal graph called ST-GFSL. We conduct comprehensive experiments on four traffic speed prediction benchmarks and the results demonstrate the effectiveness of ST-GFSL compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-05-27T12:46:52Z)
• Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities [9.891703123090528]
  We propose a novel transferable traffic forecasting framework: Adversarial Spatial-Temporal Network (DASTNet) DASTNet is pre-trained on multiple source networks and fine-tuned with the target network's traffic data. It consistently outperforms all state-of-the-art baseline methods on three benchmark datasets.
  arXiv  Detail & Related papers  (2022-02-08T03:58:39Z)
• Multistep traffic speed prediction: A deep learning based approach using latent space mapping considering spatio-temporal dependencies [2.3204178451683264]
  ITS requires a reliable traffic prediction that can provide accurate traffic prediction at multiple time steps based on past and current traffic data. A deep learning based approach has been developed using both the spatial and temporal dependencies. It has been found that the proposed approach provides accurate traffic prediction results even for 60-min ahead prediction with least error.
  arXiv  Detail & Related papers  (2021-11-03T10:17:48Z)
• An Experimental Urban Case Study with Various Data Sources and a Model for Traffic Estimation [65.28133251370055]
  We organize an experimental campaign with video measurement in an area within the urban network of Zurich, Switzerland. We focus on capturing the traffic state in terms of traffic flow and travel times by ensuring measurements from established thermal cameras. We propose a simple yet efficient Multiple Linear Regression (MLR) model to estimate travel times with fusion of various data sources.
  arXiv  Detail & Related papers  (2021-08-02T08:13:57Z)

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.