A Comparative Study of Using Spatial-Temporal Graph Convolutional Networks for Predicting Availability in Bike Sharing Schemes

Abstract

Accurately forecasting transportation demand is crucial for efficient urban traffic guidance, control and management. One solution to enhance the level of prediction accuracy is to leverage graph convolutional networks (GCN), a neural network based modelling approach with the ability to process data contained in graph based structures. As a powerful extension of GCN, a spatial-temporal graph convolutional network (ST-GCN) aims to capture the relationship of data contained in the graphical nodes across both spatial and temporal dimensions, which presents a novel deep learning paradigm for the analysis of complex time-series data that also involves spatial information as present in transportation use cases. In this paper, we present an Attention-based ST-GCN (AST-GCN) for predicting the number of available bikes in bike-sharing systems in cities, where the attention-based mechanism is introduced to further improve the performance of an ST-GCN. Furthermore, we also discuss the impacts of different modelling methods of adjacency matrices on the proposed architecture. Our experimental results are presented using two real-world datasets, Dublinbikes and NYC-Citi Bike, to illustrate the efficacy of our proposed model which outperforms the majority of existing approaches. Recently, convolutional neural networks (CNN) have been applied to extract the relationship between adjacent traffic networks whilst the recurrent neural networks (RNN) were used to arrest the temporal information. For short-term traffic prediction, fully connected long short-term memory (LSTM) [3] and CLTFP [4], two architectures mixed the long shortterm memory networks with convolutional operation, were

A Survey on Graph Neural Networks for Microservice-Based Cloud Applications

“…It is worth considering applying these GNN variants to tackle the challenges arising in microservice-based applications from different perspectives. Furthermore, attention-based mechanisms have been widely applied in other application domains with strong links to GNN-empowered designs as they have demonstrated promising results in performance improvement; see papers, such as [ 23 , 49 , 72 , 73 , 74 , 75 ]. However, limited efforts have been made regarding integrating attention mechanisms with GNNs for microservice-based applications.…”

Lane-GNN: Integrating GNN for Predicting Drivers' Lane Change Intention

“…• Attention-based temporal graph convolutional networks (Lane-GNN). Referring to the work presenting the ST-GCN architecture [25] and built upon our previous work [30], we introduce TGCN with attention mechanism, consisting of two attention temporal convolution blocks (ATCs) and a fully-connection output layer as our architecture. Each ATC consists of two temporal convolution blocks used in TCNN, with attention mechanism applied to process temporal information, as shown in Fig.…”

“…Architecture of attention temporal graph convolutional networks. The architecture is inspired and adapted from [25], [30].…”

Graph-PHPA: Graph-based Proactive Horizontal Pod Autoscaling for Microservices using LSTM-GNN

“…Motivated by the fact that Graph Convolution Networks (GCNs) have been widely used in other domains and applications, such as transportation and energy [8], [9], with promising efficacy in describing potential graphical dependency between entities in the network, we aim to leverage a graph-based approach in this paper to design a proactive horizontal pod autoscaling strategy for microservices. With this in mind, the main contributions of our work can be summarized are as follows.…”