The Graph Neural Network Model
Open accessThe DOI matches its Crossref record; 109 of the 111 references it cites were found in a registry or an index.
Abstract
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 network methods for processing the data represented in graph domains. This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, and undirected, implements a function tau(G,n) is an element of IR(m) that maps a graph G and one of its nodes n into an m-dimensional Euclidean space. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“most rely on homogeneous and static structures, which limits their ability to capture the heterogeneity and temporal evolution of real-world environments.”
From A Survey of Heterogeneous Graph Neural Networks for Cybersecurity Anomaly Detection (2025) · cites this paper as [3]
In the citing paper
“Despite notable progress in heterogeneous graph neural networks (HGNNs) for anomaly detection, several obstacles remain before such methods can be reliably deployed in real-world cybersecurity systems [3], [18], [75].”
From A Survey of Heterogeneous Graph Neural Networks for Cybersecurity Anomaly Detection (2025) · cites this paper as [3]
In the citing paper
“After convolution, feature maps consist of a large number of features that is prone to causing overfitting problem [21].”
From A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects (2022) · cites this paper as [21]
In the citing paper
“Graph neural networks (GNNs) are a type of deep learning model that are specifically designed and well-suited for analyzing complex relationships between objects represented in a graph structure [63]”
From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [63]
In the citing paper
“One of the main advantages of using the GNN for processing MTS is its ability to incorporate the information represented by vertices and edges into the learning process.”
From TVGeAN: Tensor Visibility Graph-Enhanced Attention Network for Versatile Multivariant Time Series Learning Tasks (2024) · cites this paper as [26]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Lecture Notes in Computer Science 1205
(1999) · Industrial Robot: An International Journal · doi:10.1108/ir.1999.04926fae.001 · Cited by 38,662
Neural Networks: A Comprehensive Foundation
Haykin, S. (1998) · Cited by 30,070
Wu, Y. (1999) · Technometrics · doi:10.1080/00401706.1999.10485951 · Cited by 27,221 · cited 1×
“Those techniques include random fields [42], Bayesian networks [43], statistical relational learning [44], transductive learning [45], and semisu-pervised approaches for graph processing [46].”
Neural networks and physical systems with emergent collective computational abilities.
Hopfield, J. J. (1982) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.79.8.2554 · Cited by 19,270 · cited 1×
“[47]–[50] and Hopfield neural networks [51].”
Neural networks for pattern recognition
(1994) · Choice Reviews Online · doi:10.5860/choice.31-5500 · Cited by 18,538
The anatomy of a large-scale hypertextual Web search engine
Brin, S., & Page, L. (1998) · Computer Networks and ISDN Systems · doi:10.1016/s0169-7552(98)00110-x · Cited by 16,004 · cited 8×
“More recently, there have been various approaches [17], [18] attempting to preserve the graph structured”
InfluentialParallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations
Rumelhart, D. E., McClelland, J. L., & AU (1986) · doi:10.7551/mitpress/5236.001.0001 · Cited by 15,686
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
Lafferty, J., McCallum, A., & Pereira, F. C. N. (2001) · ScholarlyCommons (University of Pennsylvania) · Cited by 12,935
Neural Networks for Pattern Recognition
Bishop, C. M. (1995) · doi:10.1093/oso/9780198538493.001.0001 · Cited by 12,287
Garreau, G. A., & Rudin, W. (1987) · The Statistician · doi:10.2307/2348852 · Cited by 10,622
Research works printed but not linked: 13
- bunke, 2000, graph matching: theoretical foundations, algorithms, and applications, Proc Vis Interface, 82
- fahlman, 1989, Advances in neural information processing systems, 2, 524
- schmitt, 1998, relating chemical structure to activity: an application of the neural folding architecture, Proc Workshop Fuzzy-Neuro Syst /Conf Eng Appl Neural Netw, 170
- k�chler, 1996, Lecture Notes in Computer Science, 1137
- wo?nica, 2006, matching based kernels for labeled graphs, Proc Int Workshop Mining Learn Graphs/ECML/PKDD, 97
- 2005, Proc Int Workshop Sub-Symbol Paradigms Structured Domains
- 2005, Proc Int l Workshop Mining Graphs Trees and Sequences
- 2006, Proc Int l Workshop Mining Graphs Trees and Sequences
- srinivasan, 1994, mutagenesis: ilp experiments in a non-determinate biological domain, Proc 9th Int l Workshop Inductive Logic Programming, 217
- scarselli, 0, The GNN Toolbox
- bua, 2002, Lecture Notes in Computer Science, 2415
- kirsten, 2002, Multirelational distance-based clustering
- 2004, Proc Int Workshop Statist Relat Learn Connect Other Fields
Cited by
Items 701–800 of 1,052
Learning and Generating Distributed Routing Protocols Using Graph-Based Deep Learning
Geyer, F., & Carle, G. (2018) · doi:10.1145/3229607.3229610 · Cited by 103
“In order to improve the training of Graph Neural Networks, Li et al. proposed Gated Graph Neural Networks (GG-NNs) in [14].”
BackgroundMethodInfluentialStructural Hole Theory in Social Network Analysis: A Review
Lin, Z., Zhang, Y., Gong, Q., Chen, Y., Oksanen, A., & Ding, A. Y. (2021) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2021.3070321 · Cited by 116
On the resilience of modern power systems: A complex network perspective
Ma, X., Zhou, H., & Li, Z. (2021) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2021.111646 · Cited by 111
Deep learning in retrosynthesis planning: datasets, models and tools
Dong, J., Zhao, M., Liu, Y., Su, Y., & Zeng, X. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab391 · Cited by 115
On the Binding Problem in Artificial Neural Networks
Greff, K., van Steenkiste, S., & Schmidhuber, J. (2020) · arXiv · doi:10.48550/arxiv.2012.05208 · Cited by 102
“Graph Neural Networks (GNNs; Scarselli et al., 2009; Pollack, 1990) are a promising approach for composition that incorporates the desired structure for relational responding at an architectural level (see Wu et al. 2020 for an overview).”
BackgroundEdgeNets: Edge Varying Graph Neural Networks
Isufi, E., Gama, F., & Ribeiro, A. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3111054 · Cited by 124
“GNNs are first concretized in [6], [7] by means of recursive neighboring label aggregations combined with pointwise nonlinearities.”
BackgroundAnatomy-aided deep learning for medical image segmentation: a review
Liu, L., Wolterink, J. M., Brüne, C., & Veldhuis, R. N. J. (2021) · Physics in Medicine and Biology · doi:10.1088/1361-6560/abfbf4 · Cited by 108
Three-Dimensional Structural Geological Modeling Using Graph Neural Networks
Hillier, M., Wellmann, F., Brodaric, B., de Kemp, E. A., & Schetselaar, E. (2021) · Mathematical Geosciences · doi:10.1007/s11004-021-09945-x · Cited by 111
Hong, Q., Ushakov, S. V., van de Walle, A., & Navrotsky, A. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2209630119 · Cited by 102
“We built a melting temperature database and an ML GNN model to predict melting temperature from chemical formula.”
MethodInfluentialDeep Models of Interactions Across Sets
Hartford, J., Graham, D. R., Leyton‐Brown, K., & Ravanbakhsh, S. (2018) · Research Explorer (The University of Manchester) · doi:10.48550/arxiv.1803.02879 · Cited by 179
“This approach builds on recent work applying convolutional neural networks to graph-structured data (Scarselli et al., 2009; Bruna et al., 2014; Duvenaud et al., 2015; Def-ferrard et al., 2016; Kipf & Welling, 2016; Hamilton et al., 2017).”
MethodTopology Optimization based Graph Convolutional Network
Yang, L., Kang, Z., Cao, X., Jin, D., Yang, B. X., & Guo, Y. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/563 · Cited by 117
A Survey of Graph Neural Networks for Electronic Design Automation
Lopera, D. S., Servadei, L., Kiprit, G. N., Hazra, S., Wille, R., & Ecker, W. (2021) · ACM/IEEE Workshop on Machine Learning for CAD (MLCAD) · doi:10.1109/mlcad52597.2021.9531070 · Cited by 118
“Recurrent Graph Neural Networks (RecGNNs) [13] process the node information recurrently by assuming that the nodes exchange information with their neighbors until a stable point is reached.”
BackgroundFarahmand, H., Xu, Y., & Mostafavi, A. (2023) · Scientific Reports · doi:10.1038/s41598-023-32548-x · Cited by 114
“Graph neural networks generalize convolution to data in a graph structure [45].”
BackgroundMobile Traffic Prediction in Consumer Applications: A Multimodal Deep Learning Approach
Jiang, W., Zhang, Y., Han, H., Huang, Z., Li, Q., & Mu, J. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3361037 · Cited by 113
“Deep learning methods have proven effective for mobile traffic prediction in recent years [10], which can be roughly divided into three categories: recurrent neural networks (RNNs), CNNs [11], and GNNs [12].”
BackgroundAnomaly Detection in Dynamic Graphs: A Comprehensive Survey
Ekle, O. A., & Eberle, W. (2024) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3669906 · Cited by 134
“The message passing mechanism in the original GNN model, as introduced by Gori et al. [51] and Scarselli et al. [126], is formally expressed in Equation 7: where ℎ ( 𝑘 ) denotes the updated embedding of node 𝑢 at layer , ( 𝑘 − 1 ) is the node embedding of 𝑢 from the previous layer 𝑘 − 1, 𝑊 (…”
InfluentialLiu, J., Kumar, A., Ba, J. L., Kiros, J., & Swersky, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.13177 · Cited by 59
“Machine learning has recently turned its attention to modeling graph-structured data using graph neural networks (GNNs) [8, 23, 16, 13, 6] that can exploit the structure of relational systems to create more accurate and generalizable predictions.”
BackgroundA Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshes
Lim, I., Dielen, A., Campen, M., & Kobbelt, L. P. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11015-4_26 · Cited by 103
Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
Jørgensen, P. B., Jacobsen, K. W., & Schmidt, M. N. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.03146 · Cited by 61
“The graph neural network model was introduced by Gori et al. (2005); Scarselli et al. (2009) and regained attention when Li et al. (2015) expanded the model for different graph problems.”
MethodSketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided DesignPreprint
Seff, A., Ovadia, Y., Zhou, W., & Adams, R. P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08506 · Cited by 150
“Graph-structured generative modeling Modern message passing networks (e.g., Gilmer et al. [12], Duvenaud et al. [8] extending the earlier work of Scarselli et al. [36]) have enabled progress in modeling of domains that exhibit relational structure, e.g., molecular chemistry and social networks.”
BackgroundScan2Mesh: From Unstructured Range Scans to 3D Meshes
Dai, A., & Nießner, M. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00572 · Cited by 128
“To this end, we leverage developments in machine learning approaches on graphs, in particular graph neural networks [28], to formulate an method to generate 3D mesh vertices, edges, and faces.”
MethodGraph Convolutional Networks with Motif-based Attention
Lee, J. B., Rossi, R. A., Kong, X., Kim, S., Koh, E., & Rao, A. B. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3357880 · Cited by 122
Universal Graph Transformer Self-Attention Networks
Nguyen, D. Q., Nguyen, T. D., & Phung, D. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3487553.3524258 · Cited by 147
“Recently, graph neural networks (GNNs) become an essential strand, forming the third direction to learn low-dimensional continuous representations for nodes and graphs [11, 20, 22, 30, 36, 40].”
BackgroundThe Universal Approximation Property: Characterization, Construction, Representation, and Existence
Kratsios, A. (2021) · Annals of Mathematics and Artificial Intelligence · doi:10.1007/s10472-020-09723-1 · Cited by 110
Understanding the Representation Power of Graph Neural Networks in Learning Graph TopologyPreprint
Dehmamy, N., Barabási, A.-Ĺ., & Yu, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.05008 · Cited by 156
“For deep fully connected networks, several recent papers have focused on understanding the benefits of depth for neural networks [11, 29, 28, 27]) with specific choice of weights.”
BackgroundFast and Deep Graph Neural Networks
Gallicchio, C., & Micheli, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5803 · Cited by 61
Rivière, B., Hönig, W., Yue, Y., & Chung, S. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2994035 · Cited by 117
“We will also compare the computational effort and performance of the Deep Set representation with deep CNN methods as well as Graph Neural Network methods [25].”
MethodGRIP: A Graph Neural Network Accelerator Architecture
Kiningham, K., Levis, P. A., & Ré, C. (2022) · IEEE Transactions on Computers · doi:10.1109/tc.2022.3197083 · Cited by 112
“message-passing where nodes are connected to dummy nodes representing a node cluster [16].”
BackgroundA Deep Reinforcement Learning Algorithm Using Dynamic Attention Model for Vehicle Routing Problems
Peng, B., Wang, J., & Zhang, Z. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-5577-0_51 · Cited by 131
Neural-Swarm2: Planning and Control of Heterogeneous Multirotor Swarms Using Learned Interactions
Shi, G., Hönig, W., Shi, X., Yue, Y., & Chung, S. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3098436 · Cited by 123
Graph Learning for Cognitive Digital Twins in Manufacturing Systems
Mortlock, T., Muthirayan, D. R. P., Yu, S.-Y., Khargonekar, P. P., & Faruque, M. A. A. (2021) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2021.3132251 · Cited by 108
CoaDTI: multi-modal co-attention based framework for drug–target interaction annotation
Huang, L., Lin, J., Liu, R., Zheng, Z., Meng, L., Chen, X., Li, X., & Wong, K.-C. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac446 · Cited by 93
Ge, S., Sun, S., Xu, H., Cheng, Q. S., & Ren, Z. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf136 · Cited by 107
Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing Its Gradient Estimator Bias
Laborieux, A., Ernoult, M., Scellier, B., Bengio, Y., Grollier, J., & Querlioz, D. (2021) · Frontiers in Neuroscience · doi:10.3389/fnins.2021.633674 · Cited by 147
Deep Graph Matching and Searching for Semantic Code Retrieval
Ling, X., Wu, L., Wang, S., Pan, G., Ma, T., Xu, F., Liu, A. X., Wu, C., & Ji, S. (2021) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3447571 · Cited by 118
“ological structures, node and/or edge attributes) as input, and output an embedding vector for each node of the input graph. There is a large body of GNN models designed to learn node representations [23, 26, 33, 35, 47, 52, 59]. With the learned node representation, various tasks on graphs can be performed such as li…”
MethodPradhyumna, P., Shreya, G., & Mohana (2021) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc51422.2021.9532631 · Cited by 111
“Scarselli [12] proposed GNN model, for processing data it extends existing neural network approaches shown in this graph domain.”
MethodDeep neural network-based relation extraction: an overview
Wang, H., Qin, K., Zakari, R. Y., Lu, G., & Yin, J. (2022) · Neural Computing and Applications · doi:10.1007/s00521-021-06667-3 · Cited by 118
“Researches have designed many kinds of DNNs, including Convolutional Neural Networks (CNNs) [28], Recurrent Neural Networks (RNNs) [11], Recursive Neural Networks [55], and Graph Neural Networks (GNNs) [52].”
BackgroundHGNN: Hyperedge-based graph neural network for MOOC Course Recommendation
Wang, X., Ma, W., Guo, L., Jiang, H., Liu, F., & Xu, C. (2022) · Information Processing & Management · doi:10.1016/j.ipm.2022.102938 · Cited by 105
Deep learning in microbiome analysis: a comprehensive review of neural network models
Przymus, P., Rykaczewski, K., Martín‐Segura, A., Truu, J., Pau, E. C. D. S., Kolev, M., Naskinova, I., Gruca, A., Sampri, A., Frohme, M., et al. (2025) · Frontiers in Microbiology · doi:10.3389/fmicb.2024.1516667 · Cited by 107
NPI-GNN: Predicting ncRNA–protein interactions with deep graph neural networks
Shen, Z.-A., Luo, T., Zhou, Y.-K., Yu, H., & Du, P.-F. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab051 · Cited by 104
Yin, J., Shen, J., Gao, X., Crandall, D., & Yang, R. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3125981 · Cited by 103
“The concept of Graph Neural Networks (GNNs) was first proposed by Scarselli et al. [35].”
Graph Representation Learning Meets Computer Vision: A Survey
Jiao, L., Chen, J., Liu, F., Yang, S., You, C., Liu, X., Li, L., & Hou, B. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3194869 · Cited by 107
“However, due to the complex dynamics of the recursive model, the original GNN [23] is inefficient to update the state of a node iteratively for a fixed point.”
BackgroundMethodInfluentialInteraction-level Membership Inference Attack Against Federated Recommender Systems
Yuan, W., Yang, C., Nguyen, Q. V. H., Cui, L., He, T., & Yin, H. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543507.3583359 · Cited by 113
“Among these recommenders, neural collaborative filtering (NCF) [11] and graph neural network (GNN) [29] are the two most widely used techniques.”
MethodA Survey on Recommender Systems Using Graph Neural Network
Anand, V., & Maurya, A. K. (2024) · ACM Transactions on Information Systems · doi:10.1145/3694784 · Cited by 127
A review of graph neural network applications in mechanics-related domains
Zhao, Y., Li, H., Zhou, H., Attar, H. R., Pfaff, T., & Li, N. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10931-y · Cited by 117
“Based on this motivation, Scarselli et al. (2009) proposed the first GNN model, which is capable of directly processing graphs.”
Recurrent Relational NetworksPreprint
Palm, R. B., Paquet, U., & Winther, O. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.08028 · Cited by 98
“Both relational networks, interaction networks and our proposed model can be seen as an instance of Graph Neural Networks (Scarselli et al., 2009), (Gilmer et al., 2017).”
MethodSun, Y., Shi, Q., Qi, L., & Zhang, Y. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.372 · Cited by 127
Action recognition based on RGB and skeleton data sets: A survey
Yue, R., Tian, Z., & Du, S. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.09.071 · Cited by 103
A mathematical guide to operator learning
Boullé, N., & Townsend, A. (2024) · Handbook of numerical analysis · doi:10.1016/bs.hna.2024.05.003 · Cited by 172
“This architecture is called graph neural operator (GNO) (Li et al., 2020a) and is inspired by graph neural network (GNN) models (Scarselli et al., 2008; Wu et al., 2020; Zhou et al., 2020).”
MethodDeep Inductive Graph Representation Learning
Rossi, R. A., Zhou, R., & Ahmed, N. K. (2018) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2878247 · Cited by 106
“There has also been some recent work on learning node embedding in dynamic networks [33], [53], [54], [55], semi-supervised network embeddings [56], [57] and methods for improving the learned representations [36], [47], [58], [59], [60], [61].”
BackgroundTHE LOGICAL EXPRESSIVENESS OF GRAPH NEURAL NETWORKS
Barceló, P., Kostylev, E. V., Monet, M., Pérez, J. E. P., Reutter, J. L., & Silva, J.-P. (2020) · HAL · Cited by 331
Relation-Aware Pedestrian Attribute Recognition with Graph Convolutional Networks
Tan, Z., Yang, Y., Wan, J., Guo, G., & Li, S. Z. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6883 · Cited by 94
“Neural Networks with Graphs: Graph Neural Networks (GNN), which are proposed in the works (Gori, Monfardini, and Scarselli 2005; Scarselli et al. 2009), are capable of extending the neural networks to process the data with a graph structure.”
BackgroundMultivariate time-series classification with hierarchical variational graph pooling
Duan, Z., Xu, H., Wang, Y., Huang, Y., Ren, A., Xu, Z., Sun, Y., & Wang, W. W. (2022) · Neural Networks · doi:10.1016/j.neunet.2022.07.032 · Cited by 102
Dong, B., Liu, Y., Fontenot, H. C., Ouf, M. M., Osman, M. G., Chong, A., Qin, S., Salim, F. D., Xue, H., Yan, D., et al. (2021) · Applied Energy · doi:10.1016/j.apenergy.2021.116856 · Cited by 99
Graph Representation Forecasting of Patient's Medical Conditions: Toward a Digital Twin
Barbiero, P., Viñas, R., & Lió, P. (2021) · Frontiers in Genetics · doi:10.3389/fgene.2021.652907 · Cited by 110
“The proposed architecture combines the qualities of generative and (Goodfellow et al., 2014) graph-based models (Scarselli et al., 2008) (see Figure 1 ).”
BackgroundMethodJoyful: Joint Modality Fusion and Graph Contrastive Learning for Multimoda Emotion Recognition
Li, D., Wang, Y., Funakoshi, K., & Okumura, M. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.996 · Cited by 112
Dual-Primal Graph Convolutional NetworksPreprint
Monti, F., Shchur, O., Bojchevski, A., Litany, O., Günnemann, S., & Bronstein, M. M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.00770 · Cited by 103
“First formulations of neural networks on graphs [15, 40] constructed learnable information diffusion processes.”
BackgroundRelational Pooling for Graph RepresentationsPreprint
Murphy, R. L., Srinivasan, B., Rao, V., & Ribeiro, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.02541 · Cited by 272
“Graph Neural Networks (GNNs) and Graph Convolutional Networks (GCNs) form an increasingly popular class of methods (Scarselli et al., 2009; Bruna et al., 2014; Duvenaud et al., 2015; Niepert et al., 2016; Atwood & Towsley, 2016; Kipf & Welling, 2017; Gilmer et al., 2017; Monti et al., 2017; Defferrard et al., 2016; Ha…”
Inference in Probabilistic Graphical Models by Graph Neural Networks
Yoon, K., Liao, R., Xiong, Y., Zhang, L., Fetaya, E., Urtasun, R., Zemel, R. S., & Pitkow, X. (2019) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf44664.2019.9048920 · Cited by 113
“GNNs are essentially an extension of recurrent neural networks that operate on graphstructured inputs [8], [9].”
BackgroundTGLSTM: A time based graph deep learning approach to gait recognition
Battistone, F., & Petrosino, A. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.05.004 · Cited by 93
“Our method, following the ideas proposed in [23,38] , is based on a deep RNN that learns not only the skeletal joints features but also the information extracted from the changes in adjacency matrices over time.”
Financial Risk Analysis for SMEs with Graph-based Supply Chain Mining
Yang, S., Zhang, Z., Zhou, J., Wang, Y., Sun, W., Zhong, X., Fang, Y., Yu, Q., & Qi, Y. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/643 · Cited by 93
Explainable predictive business process monitoring using gated graph neural networks
Harl, M. V., Weinzierl, S., Stierle, M., & Matzner, M. (2020) · Journal of Decision System · doi:10.1080/12460125.2020.1780780 · Cited by 114
“However, state-of-the-art RNNs require sequential data with a vector-oriented representation and do not grasp the possibly existing graph-oriented structure of the underlying (process) data (Scarselli et al., 2008).”
BackgroundMethodMethodology-Centered Review of Molecular Modeling, Simulation, and Prediction of SARS-CoV-2
Gao, K., Wang, R., Chen, J., Cheng, L., Frishcosy, J., Huzumi, Y., Qiu, Y., Schluckbier, T., Wei, X., & Wei, G. (2022) · Chemical Reviews · doi:10.1021/acs.chemrev.1c00965 · Cited by 95
Qi, T., Chen, L., Li, G., Li, Y., & Wang, C. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110175 · Cited by 103
Song, Z., Chen, J., Cheng, J., Chen, G., & Qi, Z. (2023) · Chemical Reviews · doi:10.1021/acs.chemrev.3c00223 · Cited by 97
TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection
Sun, H., Zhou, M., Chen, W., & Xie, W. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i5.28304 · Cited by 150
Rational Design of Earth‐Abundant Catalysts toward Sustainability
Guo, J., Haghshenas, Y., Jiao, Y., Kumar, P. V., Yakobson, B. I., Roy, A. K., Jiao, Y., Regenauer‐Lieb, K., Nguyen, D., & Xia, Z. (2024) · Advanced Materials · doi:10.1002/adma.202407102 · Cited by 101
Human Pose Estimation with Spatial Contextual InformationPreprint
Zhang, H., Ouyang, H., Liu, S., Qi, X., Shen, X., Yang, R., & Jia, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.01760 · Cited by 108
“The Graph Neural Network (GNN) was first proposed in [40].”
Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONASPreprint
Han, S., Pi, R., Xu, H., Li, Z., Kwok, J. T.-Y., & Zhang, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.09336 · Cited by 112
“Following (Scarselli et al., 2008), we add a global node to the original graph of the cell and let every node point at the global node.”
Lu, Y., Chen, Y., Zhao, D., Liu, B., Lai, Z., & Chen, M. (2020) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2020.2998497 · Cited by 99
“In 2009, they further illustrate the GNN method and prove that GNN is a continuously differentiable function and use the backpropagate algorithm to solve the model [34].”
MethodCombinatorial Learning of Robust Deep Graph Matching: An Embedding Based Approach
Wang, R., Yan, J., & Yang, X. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3005590 · Cited by 119
“In a GNN, node features are aggregated from its neighbors and often a same transfer function is shared among different nodes.”
MethodDisentangled Graph Neural Networks for Session-Based Recommendation
Li, A., Cheng, Z., Liu, F., Gao, Z., Guan, W., & Peng, Y. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3208782 · Cited by 114
“To learn the disentangled item embeddings, we employ the graph neural network techniques [32] [33] to update the item embedding factor-by-factor.”
MethodYu, X., Tang, B., & Deng, L. (2022) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2022.109848 · Cited by 94
Scalable Spatiotemporal Graph Neural Networks
Cini, A., Marisca, I., Bianchi, F. M., & Alippi, C. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i6.25880 · Cited by 153
Multiscale Channel Attention-Driven Graph Dynamic Fusion Learning Method for Robust Fault Diagnosis
Zhang, X., Liu, J., Zhang, X., & Lu, Y. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3397401 · Cited by 102
“Some graph neural networks (GNNs) [12] were also used to analyze the constructed graph data.”
MethodZhao, J., Wang, W., Huang, J. D., & Ma, X. (2025) · AIP Advances · doi:10.1063/5.0255451 · Cited by 102
A review of hyperspectral image classification based on graph neural networks
Zhao, X., Ma, J., Wang, L., Zhang, Z., Ding, Y., & Xiao, X. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11169-y · Cited by 105
SLAPS: Self-Supervision Improves Structure Learning for Graph Neural NetworksPreprint
Fatemi, B., Asri, L. E., & Kazemi, S. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.05034 · Cited by 218
“Graph neural networks (GNNs) [45] have been a key component to the success of the research in this area.”
BackgroundSi, C., Jing, Y., Wang, W., Wang, L., & Tan, T. N. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107511 · Cited by 100
“Scarselli et al. [53] proposes to recurrently update the hidden state of each node of the graph.”
BackgroundPolicy-GNN: Aggregation Optimization for Graph Neural Networks
Lai, K.-H., Zha, D., Zhou, K., & Hu, X. (2020) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3394486.3403088 · Cited by 130
“neficial to GNNs. 5 RELATED WORK This section introduces previous studies on graph neural networks, graph neural architecture search and meta-policy learning. GraphNeuralNetworks.Neural network model [34] has been studied for years to preserve the information of a graph into vector space. Based on the graph spectral t…”
BackgroundModelling High-Order Social Relations for Item Recommendation
Liu, Y., Chen, L., He, X., Peng, J., Zheng, Z., & Tang, J. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.3039463 · Cited by 64
Artificial intelligence applications in psychoradiology
Li, F. Y., Sun, H., Biswal, B. B., Sweeney, J. A., & Gong, Q. (2021) · Psychoradiology · doi:10.1093/psyrad/kkab009 · Cited by 94
“To address these issues, the concept of graph neural network (GNN) was first proposed by Scarselli and colleagues (Scarselli et al. , 2009), which is a deep learning-based method that extends existing neural networks for processing data represented in graph domains.”
SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks
Yang, L., Zhuang, J., Fu, H., Wei, X., Zhou, K., & Zheng, Y. (2021) · ACM Transactions on Graphics · doi:10.1145/3450284 · Cited by 102
“Toaddress the above issues with the existing solutions, we adopt the graph representation [Defferrard et al. 2016; Scarselli et al. 2009] to the sketch domain and present a novel method based on graph neural networks (GNNs).”
MethodLearning Selective Communication for Multi-Agent Path Finding
Ma, Z., Luo, Y., & Pan, J. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3139145 · Cited by 122
A Novel Local–Global Graph Convolutional Method for Point Cloud Semantic Segmentation
Du, Z., Ye, H., & Cao, F. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3155282 · Cited by 100
“GNNs have been successfully applied to irregular graph data [23], [25].”
MethodDynamic Dense Graph Convolutional Network for Skeleton-Based Human Motion Prediction
Wang, X., Zhang, W., Wang, C., Gao, Y., & Liu, M. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3334954 · Cited by 104
“Message Passing Neural Network (MPNN) is a general framework for deep learning on graphs [28].”
BackgroundHuang, Z., Li, K., Jiang, Y., Jia, Z., Lv, L., & Ma, Y. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112311 · Cited by 96
“The concept of graph neural networks, which dates back to 2009, was designed to process data represented in graph formats [38].”
Wang, J., Ma, A., Ma, Q., Xu, D. H., & Joshi, T. (2020) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2020.10.022 · Cited by 98
“The entire graph can be represented by pooling on all feature vectors of all nodes in the graph [33].”
BackgroundQuantifying Explainers of Graph Neural Networks in Computational Pathology
Jaume, G., Pati, P., Bozorgtabar, B., Foncubierta, A., Anniciello, A. M., Feroce, F., Rau, T., Thiran, J.-P., Gabrani, M., & Goksel, O. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00801 · Cited by 73
“We use GNNs [50, 13, 35, 24, 62, 66, 19], the conceptual analogous of 2D convolution for graph-structured data, to classify the CGs.”
MethodA Systematic Guide for Predicting Remaining Useful Life with Machine Learning
Berghout, T., & Benbouzid, M. (2022) · Electronics · doi:10.3390/electronics11071125 · Cited by 105
“AEs tasks differ from an application to another depending on data preprocessing requirements, including but not limited to denoising, compression, extraction, and neurons pruning.”
BackgroundBuilding a Digital Twin for network optimization using Graph Neural Networks
Ferriol-Galmés, M., Suárez‐Varela, J., Paillissé, J., Shi, X., Xiao, S., Cheng, X., Barlet‐Ros, P., & Cabellos‐Aparicio, A. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109329 · Cited by 108
Converting Nanotoxicity Data to Information Using Artificial Intelligence and Simulation
Yan, X., Yue, T., Winkler, D. A., Yin, Y., Zhu, H., Jiang, G., & Yan, B. (2023) · Chemical Reviews · doi:10.1021/acs.chemrev.3c00070 · Cited by 100
A survey of machine learning techniques for improving Global Navigation Satellite Systems
Mohanty, A., & Gao, G. (2024) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-024-01167-7 · Cited by 98
“• Graph neural networks (GNNs) are a class of deep learning models specifically designed for processing data represented as graphs or networks [58, 59].”
BackgroundWang, Z., Zhou, M., & Arnold, C. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa437 · Cited by 90
Global Consistent Graph Convolutional Network for Hyperspectral Image Classification
Ding, Y., Guo, Y., Chong, Y., Pan, S., & Feng, J. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3056750 · Cited by 92
“Scarselli et al. [42] introduced a method for training GNNs in a supervised manner.”
MethodFeng, J., Zeng, D., Jia, X., Zhang, X., Li, J., Liang, Y., & Jiao, L. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.05.005 · Cited by 95
Machine learning for optical fiber communication systems: An introduction and overview
Nevin, J. W., Nallaperuma, S., Shevchenko, N. A., Li, X., Faruk, M. S., & Savory, S. J. (2021) · APL Photonics · doi:10.1063/5.0070838 · Cited by 95
“45 GNNs combine graph theory with NNs in a way that draws parallels with RNNs.”
BackgroundSu, X., Hu, L., You, Z., Hu, P., Wang, L., & Zhao, B.-W. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab526 · Cited by 89
Machine learning in computational histopathology: Challenges and opportunities
Cooper, M., Ji, Z., & Krishnan, R. G. (2023) · Genes, Chromosomes and Cancer · doi:10.1002/gcc.23177 · Cited by 79
Graph neural networks for clinical risk prediction based on electronic health records: A survey
Boll, H. O., Amirahmadi, A., Ghazani, M. M., de Morais, W. O., de Freitas, E. P., Soliman, A., Etminani, F., Byttner, S., & Recamonde‐Mendoza, M. (2024) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104616 · Cited by 123
Nazir, A., Hussain, A. B., Singh, M., & Assad, A. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19694-8 · Cited by 113
Metadata
- Authors
- Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G.
- Affiliations
- University of Siena (IT)
- Hong Kong Baptist University (HK)
- University of Wollongong (AU)
- Venue
- IEEE Transactions on Neural Networks
- Published
- 2009-01
- Volume
- 20
- Issue
- 1
- Pages
- 61-80
- ISSN
- 1045-9227 (ISSN-L)
- 1941-0093
- OpenAlex
- W2116341502
- Cited by
- 9,582
- References
- 111
- Citations by year
- 2026: 1235 · 2025: 1651 · 2024: 1503 · 2023: 1398 · 2022: 1177 · 2021: 1150 · 2020: 822 · 2019: 375 · 2018: 149 · 2017: 44 · 2016: 15 · 2015: 10 · 2014: 10 · 2013: 12 · 2012: 6
- FWCI
- 13.19
- Type
- journal article
- Language
- en
- Open access
- green
- figshare.com
- Locations
- IEEE Transactions on Neural Networks (publishedVersion)
- PubMed (publishedVersion)
- HKBU Institutional Repository (Hong Kong Baptist University) (submittedVersion)
- Research Online (University of Wollongong) (submittedVersion)
- Figshare (submittedVersion, cc-by)
- Use Siena air (University of Siena) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Graph Theory and Algorithms
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- graph neural networks, graph-structured data, node embeddings, supervised learning algorithms, parameter estimation, computational cost, generalization, directed and undirected graphs
- MeSH terms
- Algorithms, Artificial Intelligence, Pattern Recognition, Automated, Regression Analysis, Reproducibility of Results, Linear Models, Databases, Factual, Neural Networks, Computer, Nonlinear Dynamics, Internet
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.