WardropNet: Traffic Flow Predictions via Equilibrium-Augmented Learning

• URL: http://arxiv.org/abs/2410.06656v1
• Date: Wed, 9 Oct 2024 08:07:29 GMT
• Title: WardropNet: Traffic Flow Predictions via Equilibrium-Augmented Learning
• Authors: Kai Jungel, Dario Paccagnan, Axel Parmentier, Maximilian Schiffer,
• Abstract summary: We introduce a novel augmented neural network architecture that allows for fast and accurate traffic flow predictions. We show how to leverage a Bregman divergence fitting the geometry of the equilibria, which allows for end-to-end learning. WardropNet outperforms pure learning-based approaches in predicting traffic equilibria for realistic and stylized traffic scenarios.
• Score: 3.592366968127126
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When optimizing transportation systems, anticipating traffic flows is a central element. Yet, computing such traffic equilibria remains computationally expensive. Against this background, we introduce a novel combinatorial optimization augmented neural network architecture that allows for fast and accurate traffic flow predictions. We propose WardropNet, a neural network that combines classical layers with a subsequent equilibrium layer: the first ones inform the latter by predicting the parameterization of the equilibrium problem's latency functions. Using supervised learning we minimize the difference between the actual traffic flow and the predicted output. We show how to leverage a Bregman divergence fitting the geometry of the equilibria, which allows for end-to-end learning. WardropNet outperforms pure learning-based approaches in predicting traffic equilibria for realistic and stylized traffic scenarios. On realistic scenarios, WardropNet improves on average for time-invariant predictions by up to 72% and for time-variant predictions by up to 23% over pure learning-based approaches.

Related papers

• FedNET: Federated Learning for Proactive Traffic Management and Network Capacity Planning [1.9818048023246968]
  FedNET is a framework for early identification of high-risk links in large-scale communication networks.<n>FedNET employs Federated Learning to model the temporal evolution of node-level traffic in a distributed manner.
  arXiv  Detail & Related papers  (2025-11-10T07:36:16Z)
• From Optimization to Prediction: Transformer-Based Path-Flow Estimation to the Traffic Assignment Problem [39.36424353588699]
  This study introduces a novel data-driven approach using deep neural networks to predict equilibrium path flows directly.<n>The Transformer-based model drastically reduces computation time, while adapting to changes in demand and network structure without the need for recalculation.<n>The model also adapts flexibly to varying demand and network conditions, supporting traffic management and enabling rapid what-if' analyses.
  arXiv  Detail & Related papers  (2025-10-22T16:45:12Z)
• A Stable Whitening Optimizer for Efficient Neural Network Training [101.89246340672246]
  Building on the Shampoo family of algorithms, we identify and alleviate three key issues, resulting in the proposed SPlus method.<n>First, we find that naive Shampoo is prone to divergence when matrix-inverses are cached for long periods.<n>Second, we adapt a shape-aware scaling to enable learning rate transfer across network width.<n>Third, we find that high learning rates result in large parameter noise, and propose a simple iterate-averaging scheme which unblocks faster learning.
  arXiv  Detail & Related papers  (2025-06-08T18:43:31Z)
• Learning traffic flows: Graph Neural Networks for Metamodelling Traffic Assignment [1.078439500019266]
  The Traffic Assignment Problem is a fundamental, yet computationally expensive, task in transportation modeling, especially for large-scale networks.<n>Traditional methods require iterative simulations to reach equilibrium, making real-time or large-scale scenario analysis challenging.<n>We propose a learning-based approach using Message-Passing Neural Networks as a metamodel to approximate the equilibrium flow of the User Equilibrium assignment.
  arXiv  Detail & Related papers  (2025-05-16T13:25:22Z)
• Multi-Class Traffic Assignment using Multi-View Heterogeneous Graph Attention Networks [5.205252810216621]
  We develop an innovative surrogate model for a traffic assignment when multi-class vehicles are involved. Our model adheres to flow conservation while delivering highly accurate predictions for link flows and utilization ratios.
  arXiv  Detail & Related papers  (2025-01-15T19:53:14Z)
• Understanding Optimization in Deep Learning with Central Flows [53.66160508990508]
  We show that an RMS's implicit behavior can be explicitly captured by a "central flow:" a differential equation. We show that these flows can empirically predict long-term optimization trajectories of generic neural networks.
  arXiv  Detail & Related papers  (2024-10-31T17:58:13Z)
• Causally-Aware Spatio-Temporal Multi-Graph Convolution Network for Accurate and Reliable Traffic Prediction [5.200012764049096]
  This study focuses on an instance of--temporal problem--traffic prediction--to demonstrate an advanced deep learning model for making accurate and reliable forecast. We propose an end-to-end traffic prediction framework that leverages three primary components to accurate and reliable traffic predictions. Experimental results on two real-world traffic datasets demonstrate that the method outperforms several state-of-the-art models in prediction accuracy.
  arXiv  Detail & Related papers  (2024-08-23T14:35:54Z)
• 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)
• Cellular Traffic Prediction Using Online Prediction Algorithms [5.416701003120508]
  This paper investigates the efficacy of live prediction algorithms for forecasting cellular network traffic in real-time scenarios. We apply two live prediction algorithms on machine learning models, one of which is recently proposed Fast LiveStream Prediction (FLSP) algorithm. Our study reveals that the FLSP algorithm can halve the required bandwidth for asynchronous data reporting compared to conventional online prediction algorithms.
  arXiv  Detail & Related papers  (2024-05-08T17:36:14Z)
• Dynamic Causal Graph Convolutional Network for Traffic Prediction [19.759695727682935]
  We propose an approach for predicting traffic that embeds time-varying dynamic network to capture finetemporal patterns of traffic data. We then use graph convolutional networks to generate traffic forecasts. Our experimental results on a real traffic dataset demonstrate the superior prediction performance of the proposed method.
  arXiv  Detail & Related papers  (2023-06-12T10:46:31Z)
• TraffNet: Learning Causality of Traffic Generation for What-if Prediction [4.604622556490027]
  Real-time what-if traffic prediction is crucial for decision making in intelligent traffic management and control. Here, we present a simple deep learning framework called TraffNet that learns the mechanisms of traffic generation for what-if pre-diction.
  arXiv  Detail & Related papers  (2023-03-28T13:12:17Z)
• Sinkhorn-Flow: Predicting Probability Mass Flow in Dynamical Systems Using Optimal Transport [89.61692654941106]
  We propose a new approach to predicting such mass flow over time using optimal transport. We apply our approach to the task of predicting how communities will evolve over time in social network settings.
  arXiv  Detail & Related papers  (2023-03-14T07:25:44Z)
• Learning GFlowNets from partial episodes for improved convergence and stability [56.99229746004125]
  Generative flow networks (GFlowNets) are algorithms for training a sequential sampler of discrete objects under an unnormalized target density. Existing training objectives for GFlowNets are either local to states or transitions, or propagate a reward signal over an entire sampling trajectory. Inspired by the TD($lambda$) algorithm in reinforcement learning, we introduce subtrajectory balance or SubTB($lambda$), a GFlowNet training objective that can learn from partial action subsequences of varying lengths.
  arXiv  Detail & Related papers  (2022-09-26T15:44:24Z)
• Real-time Object Detection for Streaming Perception [84.2559631820007]
  Streaming perception is proposed to jointly evaluate the latency and accuracy into a single metric for video online perception. We build a simple and effective framework for streaming perception. Our method achieves competitive performance on Argoverse-HD dataset and improves the AP by 4.9% compared to the strong baseline.
  arXiv  Detail & Related papers  (2022-03-23T11:33:27Z)
• Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics [85.31710759801705]
  Current practice requires expensive computational costs in model training for performance prediction. We propose a novel framework for neural network selection by analyzing the governing dynamics over synaptic connections (edges) during training. Our framework is built on the fact that back-propagation during neural network training is equivalent to the dynamical evolution of synaptic connections.
  arXiv  Detail & Related papers  (2022-01-11T20:53:15Z)
• Traffic Flow Forecast of Road Networks with Recurrent Neural Networks [0.0]
  The forecast of traffic flow is indispensable for an efficient intelligent transportation system. In our work, this prediction is performed with various recurrent neural networks. Most often the vector output model with gated recurrent units achieved the smallest error on the test set.
  arXiv  Detail & Related papers  (2020-06-08T15:17:58Z)

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.