Traffic flow prediction using multi-view graph convolution and masked attention mechanism

TL;DR: Dynamic multi-graph neural network for traffic flow prediction incorporating traffic accidents improves traffic flow prediction accuracy by incorporating dynamic multi-graphs and traffic accidents.

TL;DR: A novel dynamic multiview spatio-temporal prediction framework for traffic forecasting that incorporates local/global, short/long term spatio-temporal dependencies and dynamic changes.

TL;DR: This paper provides a comprehensive review of graph neural networks (GNN) for multi-view learning, categorizing methods into multi-relation, multi-attribute, and mixed forms, and discussing applications, datasets, and future directions in this field.

TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.

TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.

TL;DR: PyTorch as discussed by the authors is a machine learning library that provides an imperative and Pythonic programming style that makes debugging easy and is consistent with other popular scientific computing libraries, while remaining efficient and supporting hardware accelerators such as GPUs.

TL;DR: The authors used a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector.