Results 11 to 20 of about 1,903,201 (339)
Curvature graph neural network [PDF]
Information Sciences, 2022 Graph neural networks (GNNs) have achieved great success in many graph-based tasks. Much work is dedicated to empowering GNNs with the adaptive locality ability, which enables measuring the importance of neighboring nodes to the target node by a node-specific mechanism.
Li, Haifeng +5 more
openaire +2 more sources
Binarized graph neural network [PDF]
World Wide Web, 2021 Recently, there have been some breakthroughs in graph analysis by applying the graph neural networks (GNNs) following a neighborhood aggregation scheme, which demonstrate outstanding performance in many tasks. However, we observe that the parameters of the network and the embedding of nodes are represented in real-valued matrices in existing GNN-based ...
Hanchen Wang +6 more
openaire +2 more sources
The Graph Neural Network Model
IEEE Transactions on Neural Networks, 2009 Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural ...
F. Scarselli +4 more
semanticscholar +6 more sources
Stochastic Graph Neural Networks [PDF]
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020 Graph neural networks (GNNs) model nonlinear representations in graph data with applications in distributed agent coordination, control, and planning among others. Current GNN architectures assume ideal scenarios and ignore link fluctuations that occur due to environment, human factors, or external attacks. In these situations, the GNN fails to address
Zhan Gao, Elvin Isufi, Alejandro Ribeiro
openaire +2 more sources
Advances in Neural Information Processing Systems 35, 2022 We consider the bandit optimization problem with the reward function defined over graph-structured data. This problem has important applications in molecule design and drug discovery, where the reward is naturally invariant to graph permutations. The key challenges in this setting are scaling to large domains, and to graphs with many nodes.
Kassraie, Parnian +2 more
openaire +3 more sources
E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT [PDF]
IEEE/IFIP Network Operations and Management Symposium, 2021 This paper presents a new Network Intrusion Detection System (NIDS) based on Graph Neural Networks (GNNs). GNNs are a relatively new sub-field of deep neural networks, which can leverage the inherent structure of graph-based data. Training and evaluation
Wai Weng Lo +4 more
semanticscholar +1 more source
Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters [PDF]
International Conference on Information and Knowledge Management, 2020 Graph Neural Networks (GNNs) have been widely applied to fraud detection problems in recent years, revealing the suspiciousness of nodes by aggregating their neighborhood information via different relations.
Yingtong Dou +5 more
semanticscholar +1 more source
Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting [PDF]
Knowledge Discovery and Data Mining, 2022 Multivariate Time Series (MTS) forecasting plays a vital role in a wide range of applications. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have become increasingly popular MTS forecasting methods.
Zezhi Shao +3 more
semanticscholar +1 more source
LGNN: a novel linear graph neural network algorithm
Frontiers in Computational Neuroscience, 2023 The emergence of deep learning has not only brought great changes in the field of image recognition, but also achieved excellent node classification performance in graph neural networks.
Shujuan Cao +16 more
doaj +1 more source
Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting [PDF]
Proceedings of the VLDB Endowment, 2022 We all depend on mobility, and vehicular transportation affects the daily lives of most of us. Thus, the ability to forecast the state of traffic in a road network is an important functionality and a challenging task.
Zezhi Shao +6 more
semanticscholar +1 more source