… Essentially, the aim of traffic prediction is to predict a traffic-related value for a location at
a … In this section, we discuss the related work on traffic prediction problems. In time series …

… to learn the dynamic similarity between locations via traffic flow. A … temporal shifting.
Furthermore, we extend our framework from region-based traffic prediction to traffic prediction for …

… the spatial–temporal similarity. Specifically, STSF extracts spatial–temporal similarities of
different properties by combining sequence similarity with spatial–temporal trend similarity…

… , we design a novel traffic state forecasting model by manifold similarity dealing with the … of
traffic flow data, which can choose candidate data points by the manifold features of traffic flow…

… novel end-to-end framework for traffic prediction, which can model spatial, short-term and
longterm … handles dynamic spatial similarity, short-term and long-term temporal dependencies. …

… in the spatial dimension is incapable to capture sufficient spatial features. In this paper, a
traffic prediction model using Spatial-Temporal information and Traffic Pattern Similarity …

… It is natural to utilize GNNs, which have been used successfully in roadnetwork settings for
tasks such as traffic prediction [38] to take into account the structure of 𝐺. Hence, to achieve …

… Traffic prediction is the classical problem of predicting spatial-temporal data, where sensors
… between pairs of nodes, we use the cosine similarity algorithm to find the similarity between …

… First, we summarize traffic data into five types according to their difference on … spatio-temporal
data. Therefore, we survey the traffic prediction problem by looking from spatio-temporal …

… , we propose a novel traffic forecasting model, called Attention based Spatial-Temporal Graph
Neural Network (… Li, “Revisiting spatialtemporal similarity: A deep learning framework for …