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 501–600 of 1,052
Girdhar, M., Hong, J., & Moore, J. (2023) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2023.3265363 · Cited by 168
“A graph neural network (GNN) is used as a prediction model in [63] to predict the AV’s behavior, where the vehicles and their interaction in a driving scenario represent the nodes and the edges of a graph, respectively.”
MethodLarge Language Models for Test-Free Fault Localization
Yang, A. Z. H., Le Goues, C., Martins, R., & Hellendoorn, V. (2024) · Proceedings of the IEEE/ACM 46th International Conference on Software Engineering · doi:10.1145/3597503.3623342 · Cited by 144
“Recent deep learning techniques, such as GRACE [3] and FixLocator [4], encode the AST and test coverage as graph representations and learn to rank faulty methods with graph neural networks (GNN) [42].”
MethodA Restricted Black-Box Adversarial Framework Towards Attacking Graph Embedding Models
Chang, H., Rong, Y., Xu, T., Huang, W., Zhang, H., Cui, P., Zhu, W., & Huang, J. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5741 · Cited by 187
“Graph embedding models (Scarselli et al. 2009; Cui et al. 2018), which elaborate the expressive power of deep learning on graph-structure data, have achieved promising success in various domains, such as predicting properties over molecules (Duvenaud et al. 2015), biology analysis (Hamilton, Ying,…”
BackgroundSegmenting Objects From Relational Visual Data
Lu, X., Wang, W., Shen, J., Crandall, D., & Gool, L. V. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3115815 · Cited by 152
“To make this article self-contained, we first briefly introduce the basic ideas and notions of GNNs. GNNs are powerful models for collectively aggregating information from data represented in graph domains [12], [17].”
BackgroundGraph Neural Networks for Communication Networks: Context, Use Cases and Opportunities
Suárez‐Varela, J., Almasan, P., Ferriol-Galmés, M., Rusek, K., Geyer, F., Cheng, X., Shi, X., Xiao, S., Scarselli, F., Cabellos‐Aparicio, A., et al. (2022) · IEEE Network · doi:10.1109/mnet.123.2100773 · Cited by 164
“This article posits graph neural networks (GNN) [4] as a key enabler for producing accurate data-driven network models with strong generalization capabilities.”
Self-citationGraph Neural Networks for Particle Reconstruction in High Energy Physics detectorsPreprint
Ju, X., Farrell, S., Calafiura, P., Murnane, D., Prabhat, Gray, L., Klijnsma, T., Pedro, K., Cerati, G. B., Kowalkowski, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.11603 · Cited by 158
“GNNs were first introduced in [16] and have been applied to a growing variety of problems including social networks, knowledge graphs, recommender systems, and 3D shape analysis [19, 5].”
BackgroundSituation Recognition with Graph Neural Networks
Li, R., Tapaswi, M., Liao, R., Jia, J., Urtasun, R., & Fidler, S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.448 · Cited by 133
“The Graph Neural Network (GNN) proposed by [34] utilized multi-layer perceptrons (MLP) to update the hidden state.”
MethodVector Symbolic Architectures as a Computing Framework for Emerging Hardware
Kleyko, D. V., Davies, M., Frady, E. P., Kanerva, P., Kent, S. J., Olshausen, B. A., Osipov, E., Rabaey, J. M., Rachkovskij, D. A., Rahimi, A., et al. (2022) · Proceedings of the IEEE · doi:10.1109/jproc.2022.3209104 · Cited by 168
“In order to support more sophisticated symbolic computations, researchers have been embedding conventional data structures, such as graphs and key-value pairs, into neural network models [3], [4], [5].”
BackgroundOn the equivalence between graph isomorphism testing and function approximation with GNNsPreprint
Chen, Z., Villar, S., Chen, L., & Bruna, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.12560 · Cited by 251
“Graph neural networks, in all their forms, yield useful representations of graph data partly because they take into consideration the intrinsic symmetries of graphs, such as invariance and equivariance with respect to a relabeling of the nodes [25, 7, 14, 8, 10, 26, 3].”
BackgroundA Deep Neural Network Combined CNN and GCN for Remote Sensing Scene Classification
Liang, J., Deng, Y., & Zeng, D. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3011333 · Cited by 150
“Recently, a novel model called graph neural network [34] has drawn wide attention due to its ability to deal with the data in graph domain.”
BackgroundNeural Design Network: Graphic Layout Generation with Constraints
Lee, H.-Y., Jiang, L., Essa, I. A., Le, P. B., Gong, H., Yang, M., & Yang, W. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58580-8_29 · Cited by 191
Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation
Li, X., Zhou, T., Li, J., Zhou, Y., & Zhang, Z. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i3.16294 · Cited by 158
Unveiling the potential of Graph Neural Networks for robust Intrusion Detection
Pujol-Perich, D., Suarez-Varela, J., Cabellos-Aparicio, A., & Barlet-Ros, P. (2022) · ACM SIGMETRICS Performance Evaluation Review · doi:10.1145/3543146.3543171 · Cited by 118
“GNNs [6] are a novel neural network family that is particularly suitable for processing information inherently represented as graphs (e.”
BackgroundCross-dependent graph neural networks for molecular property prediction
Ma, H., Bian, Y., Rong, Y., Huang, W., Xu, T., Xie, W., Ye, G., & Huang, J. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btac039 · Cited by 157
Wang, H., Xu, T., Liu, Q., Lian, D., Chen, E., Du, D., Wu, H., & Su, W. (2019) · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3292500.3330931 · Cited by 141
“Then we adopt the message sending and receiving operations [22] of graph neural network to get the node embedding in next (k+1)-th layer.”
MethodAttacking Graph-based Classification via Manipulating the Graph Structure
Wang, B., & Gong, N. Z. (2019) · Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3319535.3354206 · Cited by 140
“normal user. Roughly speaking, there are two types of graph-based classification methods, i.e., collective classification[1, 9, 10, 14, 23, 25, 36, 40, 47, 59, 64–67, 72, 74] and graph neural network [5, 38, 52, 69]. Collective classification defines apriorreputationscore to each node based on the training dataset, as…”
MethodCovariant Compositional Networks For Learning Graphs
Kondor, R., Son, H. T., Pan, H., Anderson, B., & Trivedi, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.02144 · Cited by 89
Multi-Agent Actor-Critic with Hierarchical Graph Attention Network
Ryu, H., Shin, H., & Park, J. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6214 · Cited by 170
GNN-LSTM-based fusion model for structural dynamic responses prediction
Kuo, P.-C., Chou, Y., Li, K., Chang, W.-T., Huang, Y., & Chen, C. (2024) · Engineering Structures · doi:10.1016/j.engstruct.2024.117733 · Cited by 149
Multimodal generative AI for medical image interpretation
Rao, V. M., Hla, M., Moor, M., Adithan, S., Kwak, S., Topol, E. J., & Rajpurkar, P. (2025) · Nature · doi:10.1038/s41586-025-08675-y · Cited by 182
“Information from these graphs is typically encoded with the input using some form of graph neural network, which is a deep learning architecture that is designed to process computational graphs 68 .”
Introduction to Graph Neural Networks
Liu, Z., & Zhou, J. (2020) · Synthesis lectures on artificial intelligence and machine learning · doi:10.1007/978-3-031-01587-8 · Cited by 180
Single image 3D object reconstruction based on deep learning: A review
Fu, K., Peng, J., He, Q., & Zhang, H. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09722-8 · Cited by 156
Zhang, X., Zhang, X., Liu, J., Wu, B., & Hu, Y. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106601 · Cited by 146
Wang, J., Liu, J., Wang, H., Zhou, M., Ke, G., Zhang, L., Wu, J., Gao, Z., & Lu, D. (2024) · Nature Communications · doi:10.1038/s41467-024-46276-x · Cited by 159
“With the emergence of deep learning, graph neural networks, 30,31 and Transformers 32 – 34 have proven successfully in predicting MOF properties.”
Deep Learning for Satellite Image Time-Series Analysis: A review
Miller, L., Pelletier, C., & Webb, G. I. (2024) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2024.3393010 · Cited by 157
“Graph neural network (GNN) methods [272], [273] use this graph representation to learn a network, thus making use of these more accurate spatial and temporal representations of objects [271], [274] and allowing the identification of complex patterns and relationships [275].”
MethodDensely Connected Graph Convolutional Networks for Graph-to-Sequence Learning
Guo, Z., Zhang, Y., Teng, Z., & Lu, W. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00269 · Cited by 163
Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text
Gao, D., Li, K., Wang, R., Shan, S., & Chen, X. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01276 · Cited by 124
A reinforcement learning approach for optimizing multiple traveling salesman problems over graphs
Hu, Y., Yao, Y., & Lee, W. S. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106244 · Cited by 157
Hossain, R. R., Huang, Q., & Huang, R. (2021) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.2021.3084469 · Cited by 138
Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning
Fan, L., Wang, W., Zhu, S. C., Tang, X., & Huang, S. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00582 · Cited by 157
“Recently, graph neural networks [20,28,35,49] received increased interests since they inherit the complementary advantages of graphs (with strong representation ability) and neural networks (with end-to-end learning power).”
BackgroundSurvey on graph embeddings and their applications to machine learning problems on graphs
Makarov, I., Kiselev, D., Nikitinsky, N., & Šubelj, L. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.357 · Cited by 155
Yang, Q., Ji, H., Lü, H., & Zhang, Z. (2021) · Analytical Chemistry · doi:10.1021/acs.analchem.0c04071 · Cited by 143
Kong, Z., Jin, X., Xu, Z., & Zhang, B. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3184352 · Cited by 137
“The graph neural network (GNN) [19] aims to extend the existing DL model to unstrung data in the graph domain.”
BackgroundMethodComputer-Aided Cervical Cancer Diagnosis Using Time-Lapsed Colposcopic Images
Li, Y., Chen, J., Xue, P., Tang, C., Chang, J., Chu, C., Ma, K., Li, Q., Zheng, Y., & Qiao, Y. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.2994778 · Cited by 141
“The notation of graph neural networks (GNNs) was firstly outlined in Gori et al. [29], and further elaborated in Micheli [30] and Scarselli et al. [31].”
BackgroundZhong, H., Yu, S. S., Trinh, H. M., Lv, Y., Yuan, R. B., & Wang, Y. (2023) · Measurement · doi:10.1016/j.measurement.2022.112421 · Cited by 142
Generalizing Graph Neural Networks on Out-of-Distribution Graphs
Fan, S., Wang, X., Shi, C., Cui, P., & Wang, B. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3321097 · Cited by 177
“Graphneuralnetworksarepowerfuldeepneuralnetworksthat could perform on graph data directly [2], [3], [4], [5], [7], [10].”
BackgroundFortelny, N., & Bock, C. (2020) · Genome Biology · doi:10.1186/s13059-020-02100-5 · Cited by 135
Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks
Chen, L., Lv, B., Wang, C., Zhu, S., Tan, B., & Yu, K. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6250 · Cited by 173
“GNN is a deep neural network associated with a graph (Scarselli et al. 2009).”
BackgroundGao, Y., Li, X., Peng, H., Fang, B., & Yu, P. S. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2987019 · Cited by 126
“Graph neural network (GNN) [40], [41] is proposed to extend the deep neural network to deal with arbitrary graph-structured data.”
BackgroundMachine learning for polymer composites process simulation – a review
Cassola, S., Duhovic, M., Schmidt, T., & May, D. (2022) · Composites Part B Engineering · doi:10.1016/j.compositesb.2022.110208 · Cited by 140
A survey for solving mixed integer programming via machine learning
Zhang, J., Liu, C., Li, X., Zhen, H.-L., Yuan, M., Li, Y., & Yan, J. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.11.024 · Cited by 176
Retrosynthesis Prediction with Conditional Graph Logic NetworkPreprint
Dai, H., Li, C., Coley, C. W., Dai, B., & Song, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.01408 · Cited by 189
“Neuralization for v 1 , v 2 and w 2 Since the arguments of the energy functions w 1 , w 2 are molecules, which can be represented by graphs, one natural choice is to design the parameterization based on the recent advances in graph neural networks (GNN) [17, 18, 19, 20, 21, 22].”
BackgroundReasoning Visual Dialogs With Structural and Partial Observations
Zheng, Z., Wang, W., Qi, S., & Zhu, S. C. (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.2019.00683 · Cited by 146
“Graph Neural Networks [19, 50] draw a growing interest in the machine learning and computer vision communities, with the goal of combining structural representation of graph/graphical models with neural networks.”
BackgroundAre Graph Convolutional Networks With Random Weights Feasible?
Huang, C., Li, M., Cao, F., Fujita, H., Li, Z., & Wu, X. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3183143 · Cited by 145
“years [1], [2], [3], [4], [5], [6] by virtue of their remarkable potential in analyzing non-grid structure data that can be represented as graphs.”
BackgroundNeural network potentials for chemistry: concepts, applications and prospects
Käser, S., Vazquez-Salazar, L. I., Meuwly, M., & Töpfer, K. (2023) · Digital Discovery · doi:10.1039/d2dd00102k · Cited by 156
“122 In general, atoms are regarded as nodes (not to be confused with nodes of NN layers), each associated with a feature vector, which are connected to their neighbouring atoms within a cuto ff sphere by so-called edges.”
BackgroundHeterogeneous Multi-Layered Network Model for Omics Data Integration and Analysis
Lee, B., Zhang, S., Poleksic, A., & Xie, L. (2020) · Frontiers in Genetics · doi:10.3389/fgene.2019.01381 · Cited by 124
“…growing interests and demands in recent years, Graph Neural Networks (GNNs) have been proposed to learn the embedding of graphs (Li et al., 2015; Scarselli et al., 2008; Duvenaud et al., 2015; Kipf and Welling, 2017; Hamilton et al., 2017; Zhang et al., 2018; Ying et al., 2018; Morris et al.,…”
Random Features Strengthen Graph Neural Networks
Sato, R., Yamada, M., & Kashima, H. (2021) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9781611976700.38 · Cited by 291
Dispatch of autonomous vehicles for taxi services: A deep reinforcement learning approach
Mao, C., Liu, Y., & Shen, Z. M. (2020) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2020.102626 · Cited by 146
Adaptive Graph Auto-Encoder for General Data Clustering
Li, X., Zhang, H., & Zhang, R. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3125687 · Cited by 144
“Recent studies about graph neural networks (GNN) have achieved impressive success on graph-type data.”
BackgroundInfluentialAutomatic Floor Plan Analysis and Recognition
Pizarro, P. N., Hitschfeld, N., Sipiran, I., & Saavedra, J. M. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104348 · Cited by 132
“Graph neural networks (GNN) have also been studied to model and classify the floor plan objects, describing a way to express the nodes’ order and connectivity learned from the dataset structure [174, 175].”
Ramapuram, J., Gregorová, M., & Kalousis, A. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.02.115 · Cited by 151
Multi-Component Graph Convolutional Collaborative Filtering
Wang, X., Wang, R., Shi, C., Song, G., & Li, Q. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.6094 · Cited by 152
Learning Dual Semantic Relations With Graph Attention for Image-Text Matching
Wen, K., Gu, X., & Cheng, Q. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3030656 · Cited by 151
“As much visual information can not always be expressed as a grid-like structure such as the visual graphs, GNNs [51] is first introduced as a generalization of recursive neural networks which can directly process the graphs.”
BackgroundArtificial Intelligence‐Driven Nanoarchitectonics for Smart Targeted Drug Delivery
Bae, H., Ji, H., Konstantinov, K., Sluyter, R., Ariga, K., Kim, Y. H., & Kim, J. H. (2025) · Advanced Materials · doi:10.1002/adma.202510239 · Cited by 150
Superposition Graph Neural Network for offshore wind power prediction
Yu, M., Zhang, Z., Li, X., Yu, J. X., Gao, J., Liu, Z., You, B., Zheng, X., & Yu, R. (2020) · Future Generation Computer Systems · doi:10.1016/j.future.2020.06.024 · Cited by 139
Topology-Aware Prediction of Virtual Network Function Resource Requirements
Mijumbi, R., Hasija, S., Davy, S., Davy, A., Jennings, B., & Boutaba, R. (2017) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2017.2666781 · Cited by 130
“The next two sections introduce the concept of GNNs and how it has been used to develop a system that forecasts the resource requirements of each VNFC, in order to obtain advance information of the VNFC’s upcoming resource needs, allowing an orchestration entity to satisfy such needs just in time.”
Knowledge Base Completion with Out-of-Knowledge-Base Entities: A Graph Neural Network Approach
Hamaguchi, T., Oiwa, H., Shimbo, M., & Matsumoto, Y. (2018) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.f-h72 · Cited by 131
GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation
Ma, X., Zhang, T., & Xu, C. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00846 · Cited by 127
“The GNN is first proposed in [31, 64] as a trainable recurrent message passing whose fixed points could be adjusted discriminatively.”
BackgroundA deeper graph neural network for recommender systems
Yin, R., Li, K., Zhang, G., & Lü, J. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.105020 · Cited by 146
Modulation Recognition With Graph Convolutional Network
Liu, Y., Liu, Y., & Yang, C. (2020) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2019.2963828 · Cited by 135
“Since Scarselli et al. proposed the prototype of graph neural network (GNN) in 2009 [13], researchers have developed many variations of GNN such as GCN, graph attention network, graph auto-encoder, graph generative network and graph spatial-temporal network.”
BackgroundGraph convolutional networks for graphs containing missing features
Taguchi, H., Liu, X., & Murata, T. (2020) · Future Generation Computer Systems · doi:10.1016/j.future.2020.11.016 · Cited by 160
Hyperbolic Graph Attention Network
Zhang, Y., Wang, X., Shi, C., Jiang, X., & Ye, Y. F. (2021) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2021.3081431 · Cited by 219
Learning to Pre-train Graph Neural Networks
Lu, Y., Jiang, X., Fang, Y., & Shi, C. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i5.16552 · Cited by 183
“Originally proposed (Marco, Gabriele, and Franco 2005; Scarselli et al. 2008) as a framework of utilizing neural networks to learn node representations on graphs, this concept is extended to convolution neural networks using spectral methods (Defferrard, Bresson, and Vandergheynst 2016; Bruna et al.”
MethodMulti-view graph convolutional networks with attention mechanism
Yao, K., Liang, J., Liang, J., Li, M., & Cao, F. (2022) · Artificial Intelligence · doi:10.1016/j.artint.2022.103708 · Cited by 138
Graph neural network for groundwater level forecasting
Bai, T., & Tahmasebi, P. (2022) · Journal of Hydrology · doi:10.1016/j.jhydrol.2022.128792 · Cited by 141
Hierarchical Reinforcement Learning: A Survey and Open Research Challenges
Hutsebaut-Buysse, M., Mets, K., & Latré, S. (2022) · Machine Learning and Knowledge Extraction · doi:10.3390/make4010009 · Cited by 129
“For example, Graph Neural Networks (GNN) [114,115] are capable of directly working with data structured as a graph.”
BackgroundToward autonomous laboratories: Convergence of artificial intelligence and experimental automation
Xie, Y., Sattari, K., Zhang, C., & Lin, J. (2022) · Progress in Materials Science · doi:10.1016/j.pmatsci.2022.101043 · Cited by 145
Weisfeiler and Lehman Go Topological: Message Passing Simplicial NetworksPreprint
Bodnar, C., Frasca, F., Wang, Y. G., Otter, N., Montúfar, G., Lió, P., & Bronstein, M. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.03212 · Cited by 166
“Graph neural networks (GNNs), which trace their origins to the 1990s (Sperduti, 1994; Goller & Kuchler, 1996; Gori et al., 2005; Scarselli et al., 2009; Bruna et al., 2014; Li et al., 2015), have recently achieved great success in learning tasks with graph-structured data.”
BackgroundCollaborative Motion Prediction via Neural Motion Message Passing
Hu, Y., Chen, S., Zhang, Y., & Gu, X. (2020) · 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/cvpr42600.2020.00635 · Cited by 153
Deep dive into machine learning density functional theory for materials science and chemistry
Fiedler, L., Shah, K., Bußmann, M., & Cangi, A. (2022) · Physical Review Materials · doi:10.1103/physrevmaterials.6.040301 · Cited by 153
Conditional Directed Graph Convolution for 3D Human Pose Estimation
Hu, W., Zhang, C., Zhan, F., Zhang, L., & Wong, T. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475219 · Cited by 152
“GCNs [9, 13, 37] generalize conventional convolution operators to graphs, and can be roughly categorized into spectral [9, 20, 21] and spatial [1, 11, 13] perspective GCNs.”
BackgroundKheddar, H., Hemis, M., Himeur, Y., Megías, D., & Amira, A. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127528 · Cited by 146
“The function 𝑓 is the transition function that projects these inputs onto a 𝑑 -dimensional space [99].”
BackgroundWang, R., Yan, J., & Yang, X. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3078053 · Cited by 180
Contextualized Graph Attention Network for Recommendation with Item Knowledge Graph
Liu, Y., Yang, S., Xu, Y., Miao, C., Wu, M., & Zhang, J. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3082948 · Cited by 157
“Recurrent graph neural networks [41], [42], [43] are the pioneer GNNmethods.”
BackgroundMethodMTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences
Yang, J., Wang, Y., Yi, R., Zhu, Y., Rehman, A., Zadeh, A., Poria, S., & Morency, L. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.79 · Cited by 179
“Graph Neural Networks Graph Neural Network (GNN) was introduced in (Gori et al., 2005; Scarselli et al., 2008) with an attempt to extend deep neural networks to handle graph-structured data.”
BackgroundExploring graph neural networks for semantic enrichment: Room type classification
Wang, Z., Sacks, R., & Yeung, T. (2021) · Automation in Construction · doi:10.1016/j.autcon.2021.104039 · Cited by 135
Multi-View Transformer for 3D Visual Grounding
Huang, S., Chen, Y., Jia, J., & Wang, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01508 · Cited by 113
“Referit3D [1] uses GRU [6] to extract text features, and makes use of GNN [27] to model the relationship between objects.”
Deep Learning for Zero-day Malware Detection and Classification: A Survey
Deldar, F., & Abadi, M. (2023) · ACM Computing Surveys · doi:10.1145/3605775 · Cited by 158
Xu, Z., Zhou, Y., Kalogerakis, E., Landreth, C., & Singh, K. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392379 · Cited by 126
Learning Transferable Cooperative Behavior in Multi-Agent Teams
Agarwal, A., Kumar, S., Sycara, K. P., & Lewis, M. (2020) · Adaptive Agents and Multi-Agents Systems · doi:10.65109/edcb3795 · Cited by 167
Machine-Learning–Based Column Selection for Column Generation
Morabit, M., Desaulniers, G., & Lodi, A. (2021) · Transportation Science · doi:10.1287/trsc.2021.1045 · Cited by 172
“They were initially introduced by Gori et al. (2005) and further developed by Scarselli et al. (2009).”
BackgroundA spatial attentive and temporal dilated (SATD) GCN for skeleton‐based action recognition
Zhang, J., Ye, G., Tu, Z., Qin, Y., Qin, Q., Zhang, J., & Liu, J. (2021) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12012 · Cited by 138
“[34] first proposed a graph neural network (GNN) to handle the graph structure data, as GNN is a trainable model which is able to aggregate the vertex information in terms of the manually designed rules in the graph structure.”
Internet Financial Fraud Detection Based on Graph Learning
Li, R., Liu, Z., Ma, Y., Yang, D. L., & Sun, S. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2022.3189368 · Cited by 164
“The work of literature [21], [22] is performed on directed acyclic graphs, the work of literature [23] is performed on undirected graphs, and SSE [24] improves the scalability and can be embedded in large graphs.”
BackgroundShi, X., Zhang, Y., Pujahari, A., & Mishra, S. K. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125423 · Cited by 130
GraphNorm: A Principled Approach to Accelerating Graph Neural Network TrainingPreprint
Cai, T., Luo, S., Xu, K., He, D., Liu, T., & Wang, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.03294 · Cited by 167
“Recently, there has been a surge of interest in Graph Neural Networks (GNNs) for learning with graphs (Gori et al., 2005; Scarselli et al., 2008; Hamilton et al., 2017; Kipf & Welling, 2017; Velickovic et al., 2018; Xu et al., 2018; Ying et al., 2021).”
BackgroundMeng, W., Yang, D., & Xiao, Y. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401098 · Cited by 125
Cheng, R., & Li, Q. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i1.16077 · Cited by 173
“Most GNNs, including GCN (Scarselli et al. 2009) and GAT (Vaswani et al. 2017), generate relational embeddings via linear aggrega-tors.”
BackgroundMethodAdvanced Deep Learning Models for 6G: Overview, Opportunities, and Challenges
Jiao, L., Shao, Y., Sun, L., Liu, F., Yang, S., Ma, W., Li, L., Liu, X., Hou, B., Zhang, X., et al. (2024) · IEEE Access · doi:10.1109/access.2024.3418900 · Cited by 148
AGFCN:A bearing fault diagnosis method for high-speed train bogie under complex working conditions
He, D., Wu, J., Jin, Z., Huang, C., Wei, Z., & Yi, C. (2025) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2025.110907 · Cited by 125
Hierarchical Human Parsing With Typed Part-Relation Reasoning
Wang, W., Zhu, H., Dai, J., Pang, Y., Shen, J., & Shao, L. (2020) · 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/cvpr42600.2020.00895 · Cited by 141
Co-Embedding of Nodes and Edges With Graph Neural Networks
Jiang, X., Zhu, R., Ji, P., & Li, S. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3029762 · Cited by 149
Vulnerability Detection with Graph Simplification and Enhanced Graph Representation Learning
Wen, X.-C., Chen, Y., Gao, C., Zhang, H., Zhang, J. M., & Liao, Q. (2023) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse48619.2023.00191 · Cited by 168
Learning Graph-Level Representation for Drug Discovery
Li, J., Cai, D., & He, X. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.03741 · Cited by 59
“Graph-based Neural networks have previously introduced in(Gori, Monfardini, and Scarselli 2005; Scarselli et al. 2009) as a form of recurrent neural network.”
BackgroundNikolentzos, G., Siglidis, G., & Vazirgiannis, M. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13225 · Cited by 172
Review on the Applications of Deep Learning in the Analysis of Gastrointestinal Endoscopy Images
Du, W., Rao, N., Liu, D., Jiang, H., Luo, C., Li, Z., Gan, T., & Zeng, B. (2019) · IEEE Access · doi:10.1109/access.2019.2944676 · Cited by 129
“there are many other efficient networks such as recurrent neural networks (RNNs), graph neural networks (GNNs) [44], principle component analysis network (PCANet) [45] and canonical correlation analysis network (CCANet) [46] that have not yet been used in GI image analysis at present.”
BackgroundZhao, X., Yao, J., Deng, W., Ding, P., Zhuang, J., & Liu, Z. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3161674 · Cited by 123
“The concept of GNNs was first proposed by Scarselli et al. [21].”
BackgroundLazcano, A., Herrera, P. J., & Monge, M. (2023) · Mathematics · doi:10.3390/math11010224 · Cited by 145
Speeding Up Graph Edit Distance Computation through Fast Bipartite Matching
Fankhauser, S., Riesen, K., & Horst Bunke, A. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-20844-7_11 · Cited by 150
“In other approaches, artificial neural networks, relaxation labeling techniques, and genetic algorithms have been used to map the nodes of one graph to the nodes of another graph such that the edge structure is preserved as accurately as possible [5, 6 ,7].”
MethodHierarchical attentive knowledge graph embedding for personalized recommendation
Sha, X., Sun, Z., & Zhang, J. (2021) · Electronic Commerce Research and Applications · doi:10.1016/j.elerap.2021.101071 · Cited by 127
TRANSPARENT COGNITIVE TECHNOLOGIES TO ENSURE SUSTAINABLE SOCIETY DEVELOPMENT
Kwilinski, A. S., Tkachenko, V., & Kuzior, A. (2019) · Journal of Security and Sustainability Issues · doi:10.9770/jssi.2019.9.2(15 · Cited by 124
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.