Graph-Partitioning-Based Diffusion Convolutional Recurrent Neural Network for Large-Scale Traffic Forecasting

Mallick, Tanwi; Balaprakash, Prasanna; Rask, Eric; Macfarlane, Jane

doi:10.1177/0361198120930010

Cited by 68 publications

(20 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [22,23,24] including the recent state-of-the-art UQ estimation work [25]. The default hyperparameter configuration used for DCRNN is as follows: batch size -64; filter type -dual/bidirectional random walk (captures both the upstream and the downstream traffic dynamic); number of diffusion steps -2; RNN layers -2; RNN units per layer-64; optimizer -Adam; threshold for gradient clipping -5; initial learning rate -0.01; and learning rate decay -0.1.…”

Section: Resultsmentioning

confidence: 99%

Deep-Ensemble-Based Uncertainty Quantification in Spatiotemporal Graph Neural Networks for Traffic Forecasting

Mallick¹,

Balaprakash²,

Macfarlane³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Deep-learning-based data-driven forecasting methods have produced impressive results for traffic forecasting. A major limitation of these methods, however, is that they provide forecasts without estimates of uncertainty, which are critical for real-time deployments. We focus on a diffusion convolutional recurrent neural network (DCRNN), a state-of-the-art method for short-term traffic forecasting. We develop a scalable deep ensemble approach to quantify uncertainties for DCRNN. Our approach uses a scalable Bayesian optimization method to perform hyperparameter optimization, selects a set of high-performing configurations, fits a generative model to capture the joint distributions of the hyperparameter configurations, and trains an ensemble of models by sampling a new set of hyperparameter configurations from the generative model. We demonstrate the efficacy of the proposed methods by comparing them with other uncertainty estimation techniques. We show that our generic and scalable approach outperforms the current state-of-the-art Bayesian and number of other commonly used frequentist techniques.

show abstract

Section: Resultsmentioning

confidence: 99%

Deep-Ensemble-Based Uncertainty Quantification in Spatiotemporal Graph Neural Networks for Traffic Forecasting

Mallick¹,

Balaprakash²,

Macfarlane³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The latter model has attracted much attention due to its superior efficiency in pattern classification problem solving. We find a range of studies, including [31] and [48], where a CNN is merged with an RNN in a deep neural model that aims at time series forecasting. The role of a CNN in such a model is to extract features that are used to train an RNN forecasting model [26].…”

Section: Related Work On Time Series Forecastingmentioning

confidence: 99%

Long Short-term Cognitive Networks

Nápoles¹,

Grau²,

Jastrzębska³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we present a recurrent neural system named Long Short-term Cognitive Networks (LSTCNs) as a generalisation of the Short-term Cognitive Network (STCN) model. Such a generalisation is motivated by the difficulty of forecasting very long time series in an efficient, greener fashion. The LSTCN model can be defined as a collection of STCN blocks, each processing a specific time patch of the (multivariate) time series being modelled. In this neural ensemble, each block passes information to the subsequent one in the form of a weight matrix referred to as the prior knowledge matrix. As a second contribution, we propose a deterministic learning algorithm to compute the learnable weights while preserving the prior knowledge resulting from previous learning processes. As a third contribution, we introduce a feature influence score as a proxy to explain the forecasting process in multivariate time series. The simulations using three case studies show that our neural system reports small forecasting errors while being up to thousands of times faster than state-of-the-art recurrent models.

show abstract

“…It was able to predict the traffic flow of one city using the data collected from another. In our work, instead of using the partition for cities [33], we partition the graph based on the spatial recognition of the rescuers when performing the search task.…”

Section: Related Workmentioning

confidence: 99%

Designing Context-Sensitive Norm Inverse Reinforcement Learning Framework for Norm-Compliant Autonomous Agents

Guo

Wang

Hughes

et al. 2020

2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

View full text Add to dashboard Cite

To build an agent providing assistance to human rescuers in an urban search and rescue task, it is crucial to understand not only human actions but also human beliefs that may influence the decision to take these actions. Developing data-driven models to predict a rescuer's strategies for navigating the environment and triaging victims requires costly data collection and training for each new environment of interest. Transfer learning approaches can be used to mitigate this challenge, allowing a model trained on a source environment/task to generalize to a previously unseen target environment/task with few training examples. In this paper, we investigate transfer learning (a) from a source environment with smaller number of types of injured victims to one with larger number of victim injury classes and (b) from a smaller and simpler environment to a larger and more complex one for navigation strategy. Inspired by hierarchical organization of human spatial cognition, we used graph division to represent spatial knowledge, and Transfer Learning Diffusion Convolutional Recurrent Neural Network (TL-DCRNN), a spatial and temporal graph-based recurrent neural network suitable for transfer learning, to predict navigation. To abstract the rescue strategy from a rescuer's field-of-view stream, we used attention-based LSTM networks. We experimented on various transfer learning scenarios and evaluated the performance using mean average error. Results indicated our assistant agent can improve predictive accuracy and learn target tasks faster when equipped with transfer learning methods.

show abstract

Graph-Partitioning-Based Diffusion Convolutional Recurrent Neural Network for Large-Scale Traffic Forecasting

Cited by 68 publications

References 45 publications

Deep-Ensemble-Based Uncertainty Quantification in Spatiotemporal Graph Neural Networks for Traffic Forecasting

Deep-Ensemble-Based Uncertainty Quantification in Spatiotemporal Graph Neural Networks for Traffic Forecasting

Long Short-term Cognitive Networks

Designing Context-Sensitive Norm Inverse Reinforcement Learning Framework for Norm-Compliant Autonomous Agents

Contact Info

Product

Resources

About