… graph representation learning method (Hamilton et al., 2017a), we propose an inductive
graph-based neural network … information for directed and undirected graphs, which explores two …

… in the graph. Our architecture couples the recently proposed Gated Graph Neural Networks
with … baselines in generation from AMR graphs and syntax-based neural machine translation. …

… in their historical sequences. In this work, we propose a graph neural network model called
SURGE (short for SeqUential Recommendation with Graph neural nEtworks) to address …

… , sequential GNN (SGNN), and its extended model, ESGNN. Specifically, we build individual
graphs … long short-term memory network (Bi-LSTM) to extract the sequential features of each …

… Unlike graph neural networks that restrict the information exchange between immediate …
relationship between SAN and graph neural networks inspires our work. Graph Transformer …

… graph representation learning [18], we propose a novel method named Dynamic Graph
Neural Network for Sequential … and items through a dynamic graph. The framework of DGSR is …

… , and the other one is how to capture long-distance dependencies for a graph sequence
as input with an attention mechanism. Finally, we propose a graph sequence neural network …

… a sequential output problem. A secondary contribution is highlighting that Graph Neural
Networks (and further extensions we develop here) are a broadly useful class of neural network …

… graph neural networks (GNNs) [7][8] and graph CNNs (GCNNs) [9] have introduced new ideas
to the whole road network … and output of our problem as sequential graphs. However, this …

… graph neural network (MA-GNN) to capture both the long- and short-term user interests.
Specifically, we apply a graph neural network to … utilize a shared memory network to capture the …