Position-Aware Convolutional Networks for Traffic Prediction

TL;DR

This paper introduces a position-aware neural network for traffic prediction that integrates spatial position embeddings with feature extraction, significantly improving accuracy over existing methods.

Contribution

It presents a novel position embedding technique applied to traffic prediction, enabling position-specific processing within a convolutional network.

Findings

Outperforms previous methods on real-world datasets

Uses fewer data sources while maintaining high accuracy

Demonstrates the effectiveness of position embeddings in traffic modeling

Abstract

Forecasting the future traffic flow distribution in an area is an important issue for traffic management in an intelligent transportation system. The key challenge of traffic prediction is to capture spatial and temporal relations between future traffic flows and historical traffic due to highly dynamical patterns of human activities. Most existing methods explore such relations by fusing spatial and temporal features extracted from multi-source data. However, they neglect position information which helps distinguish patterns on different positions. In this paper, we propose a position-aware neural network that integrates data features and position information. Our approach employs the inception backbone network to capture rich features of traffic distribution on the whole area. The novelty lies in that under the backbone network, we apply position embedding technique used in neural language processing to represent position information as embedding vectors which are learned during the training. With these embedding vectors, we design position-aware convolution which allows different kernels to process features of different positions. Extensive experiments on two real-world datasets show that our approach outperforms previous methods even with fewer data sources.