… in the graph. Our architecture couples the recently proposed Gated GraphNeuralNetworks with … baselines in generation from AMR graphs and syntax-based neural machine translation. …
J Chang, C Gao, Y Zheng, Y Hui, Y Niu… - Proceedings of the 44th …, 2021 - dl.acm.org
… in their historical sequences. In this work, we propose a graphneuralnetwork model called SURGE (short for SeqUential Recommendation with GraphneuralnEtworks) to address …
K Zhao, L Huang, R Song, Q Shen, H Xu - Algorithms, 2021 - mdpi.com
… , 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 …
D Cai, W Lam - Proceedings of the AAAI conference on artificial …, 2020 - ojs.aaai.org
… Unlike graphneuralnetworks that restrict the information exchange between immediate … relationship between SAN and graphneuralnetworks inspires our work. Graph Transformer …
M Zhang, S Wu, X Yu, Q Liu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
… graph representation learning [18], we propose a novel method named Dynamic Graph NeuralNetwork for Sequential … and items through a dynamic graph. The framework of DGSR is …
Z Lu, W Lv, Z Xie, B Du, G Xiong, L Sun… - ACM Transactions on …, 2022 - dl.acm.org
… , and the other one is how to capture long-distance dependencies for a graphsequence as input with an attention mechanism. Finally, we propose a graphsequenceneuralnetwork …
… a sequential output problem. A secondary contribution is highlighting that GraphNeural Networks (and further extensions we develop here) are a broadly useful class of neuralnetwork …
Z Xie, W Lv, S Huang, Z Lu, B Du, R Huang - IEEE Access, 2019 - ieeexplore.ieee.org
… graphneuralnetworks (GNNs) [7][8] and graph CNNs (GCNNs) [9] have introduced new ideas to the whole road network … and output of our problem as sequentialgraphs. However, this …
… graphneuralnetwork (MA-GNN) to capture both the long- and short-term user interests. Specifically, we apply a graphneuralnetwork to … utilize a shared memory network to capture the …