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 601–700 of 1,052
Cross-modal knowledge reasoning for knowledge-based visual question answering
Yu, J., Zhu, Z., Wang, Y., Zhang, W., Hu, Y., & Tan, J. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107563 · Cited by 148
Yang, C. H., Liu, J., & Shi, C. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3450068 · Cited by 181
“The concept of GNNwas proposed [21] before 2010 and has become a rising topic since the emergence of GCN [11].”
BackgroundIs neuro-symbolic AI meeting its promises in natural language processing? A structured review
Hamilton, K., Nayak, A., Božić, B., & Longo, L. (2024) · Semantic Web · doi:10.3233/sw-223228 · Cited by 88
“– Graph Neural Network Model [56] - early GNN architecture similar to GCN.”
MethodCascaded Parsing of Human-Object Interaction Recognition
Zhou, T., Qi, S., Wang, W., Shen, J., & Zhu, S. C. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3049156 · Cited by 132
“An essential branch of DNNs [62], [63], i.e ., graph neural networks (GNNs), was developed to allow end-to-end learning over graphs and has gained widespread attention in recent years.”
BackgroundMulti-Robot Collaborative Perception With Graph Neural Networks
Zhou, Y., Xiao, J., Zhou, Y., & Loianno, G. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3141661 · Cited by 152
“Various types of graph neural networks have been proposed, including GNN [2], Convolutional GNNs [3], Graph Attention Networks [4].”
BackgroundMethodGraph neural network-accelerated Lagrangian fluid simulation
Li, Z., & Farimani, A. B. (2022) · Computers & Graphics · doi:10.1016/j.cag.2022.02.004 · Cited by 148
AUC-oriented Graph Neural Network for Fraud Detection
Huang, M., Liu, Y., Ao, X., Li, K., Chi, J., Feng, J., Yang, H., & He, Q. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3512178 · Cited by 121
“Benefited by the capability of mining profound dependence and correlations between entities, Graph Neural Networks (GNNs) [12, 33] have been broadly implemented in fraud detection tasks [7, 16, 21, 48, 50, 52].”
BackgroundObaido, G., Mienye, I. D., Egbelowo, O. F., Emmanuel, I. D., Ogunleye, A., Ogbuokiri, B., Mienye, P., & Aruleba, K. (2024) · Machine Learning with Applications · doi:10.1016/j.mlwa.2024.100576 · Cited by 155
Cascade Graph Neural Networks for RGB-D Salient Object Detection
Luo, A., Li, X., Yang, F., Jiao, Z., Cheng, H., & Lyu, S. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58610-2_21 · Cited by 136
IoT-Based Android Malware Detection Using Graph Neural Network With Adversarial Defense
Yumlembam, R., Issac, B., Jacob, S. M., & Yang, L. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3188583 · Cited by 120
“Different centrality measures are extracted from the API graph to train a GNN [11], [12] to generate graph embedding of each Android Application.”
MethodGraph Neural Networks for Routing Optimization: Challenges and Opportunities
Jiang, W., Han, H., Zhang, Y., Wang, J., He, M., Gu, W., Mu, J., & Cheng, X. (2024) · Sustainability · doi:10.3390/su16219239 · Cited by 142
“GNNs [67] are based on the message-passing mechanism, which updates the state of a particular node with information from its neighbors.”
Multiple Rumor Source Detection with Graph Convolutional Networks
Dong, M., Zheng, B., Quoc Viet Hung, N., Su, H., & Li, G. (2019) · Proceedings of the 28th ACM International Conference on Information and Knowledge Management · doi:10.1145/3357384.3357994 · Cited by 119
RelEx: A Model-Agnostic Relational Model Explainer
Zhang, Y., DeFazio, D., & Ramesh, A. (2021) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3461702.3462562 · Cited by 148
“non-Euclidean, graph-structured data. Relational Models include Statistical relational learning (SRL) methods [1], stochastic blockmodels, and the more recently developed Graph Neural Networks (GNNs) [2]. These relational models can be applied for a variety of tasks dealing with structured data, e.g. molecule classific…”
BackgroundJointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization
Liu, D., Qu, X., Liu, X.-Y., Dong, J., Zhou, P., & Xu, Z. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3414026 · Cited by 154
“Graph neural network (GNN) [34] is an extension for recursive neural networks and random walk based models for graph structured data.”
MethodLearning Video Moment Retrieval Without a Single Annotated Video
Gao, J., & Xu, C. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3075470 · Cited by 128
A generative architectural and urban design method through artificial neural networks
Zheng, H. R., & Yuan, P. F. (2021) · Building and Environment · doi:10.1016/j.buildenv.2021.108178 · Cited by 126
Neural Subgraph MatchingPreprint
Rex, Ying, Lou, Z., You, J., Wen, C., Canedo, A., & Leskovec, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.03092 · Cited by 146
“Earlier work (Scarselli et al., 2008) has demonstrated the potential of GNN in small-scale subgraph matching, showing advantage of GNN over feed forward neural networks.”
BackgroundGAG: Global Attributed Graph Neural Network for Streaming Session-based Recommendation
Qiu, R., Yin, H., Huang, Z. H., & Chen, T. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401109 · Cited by 145
Fully Convolutional Scene Graph Generation
Liu, H., Yan, N., Mortazavi, M., & Bhanu, B. (2021) · 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/cvpr46437.2021.01138 · Cited by 149
“[6] utilized graph neural networks [46] to infer relationships.”
MLCAD: A Survey of Research in Machine Learning for CAD Keynote Paper
Rapp, M., Amrouch, H., Lin, Y., Yu, B., Pan, D. Z., Wolf, M., & Henkel, J. (2021) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2021.3124762 · Cited by 140
“We extract two special types of NNs: 1) Graph-NNs [8] where the input is represented as a graph consisting of vertices and edges 2) and generative adversarial networks (GANs).”
MethodDeep learning-based 3D reconstruction: a survey
Samavati, T., & Soryani, M. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10399-2 · Cited by 136
“This block deforms the up-sampled mesh to produce a refined 3D model with finer details by utilizing GCN (Scarselli et al. 2008).”
MethodUnifying Short and Long-Term Tracking with Graph Hierarchies
Cetintas, O., Brasó, G., & Leal-Taixé, L. (2023) · 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/cvpr52729.2023.02191 · Cited by 162
“We use a graph neural network (GNN) [6,15,41] to process those into short tracklets, and then build new graphs to generate increasingly longer trajectories at every level of our hierarchy.”
MethodSemantic understanding and prompt engineering for large-scale traffic data imputation
Zhang, K., Zhou, F., Wu, L., Xie, N., & He, Z. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102038 · Cited by 124
Federated learning for network attack detection using attention-based graph neural networks
Jianping, W., Guangqiu, Q., Wu, C., Jiang, W., & Jin, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-70032-2 · Cited by 133
“For graph data with irregular spatial structure, researchers 7–10 tried to generalize neural networks to handle graphs with arbitrary structures, thus introducing graph neural networks 11 .”
MethodCan Graph Neural Networks Count Substructures?Preprint
Chen, Z., Chen, L., Villar, S., & Bruna, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.04025 · Cited by 216
“In recent years, graph neural networks (GNNs) have achieved empirical success on processing data from various fields such as social networks, quantum chemistry, particle physics, knowledge graphs and combinatorial optimization [4, 5, 9, 10, 12, 13, 29, 31, 47, 55, 58, 66, 67, 69, 70, 71, 73, 74].”
BackgroundContext-Aware Visual Compatibility Prediction
Cucurull, G., Taslakian, P., & Vázquez, D. (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.2019.01290 · Cited by 131
“[29].”
Spatial Graph Convolutional Networks
Danel, T., Spurek, P., Tabor, J., Śmieja, M., Struski, Ł., Słowik, A., & Maziarka, Ł. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-63823-8_76 · Cited by 141
MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks
Pata, J., Duarte, J., Vlimant, J.-R., Maurizio Pierini, B., & Spiropulu, M. (2021) · The European Physical Journal C · doi:10.1140/epjc/s10052-021-09158-w · Cited by 132
“Having built the graph dynamically, we now use a variant of message passing [20, 22, 58, 59] to create hidden encoded states G (xi,Ai j|w) = hi of the input elements taking into account the graph structure.”
MethodDeep Reinforcement Learning for Combinatorial Optimization: Covering Salesman Problems
Li, K., Zhang, T., Wang, R., Wang, Y., Han, Y., & Wang, L. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3103811 · Cited by 116
“Current state-of-the-art approaches mainly use sequence-to-sequence networks [17] and Graph Neural Networks (GNNs) [18] for combinatorial optimization.”
MethodAlchemy: A Quantum Chemistry Dataset for Benchmarking AI ModelsPreprint
Chen, G., Chen, P., Hsieh, C., Lee, C., Liao, B., Liao, R., Liu, W., Qiu, J., Sun, Q., Tang, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.09427 · Cited by 129
“Recently, novel techniques such as Graph Neural Networks (GNNs) (Gori et al., 2005; Scarselli et al., 2009) could automatically extract meaningful features from the molecular graphs without resorting to the more traditional approach of manually designing descriptors such as fingerprints.”
MethodAdaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency Detection
Zhang, K., Li, T., Shen, S., Liu, B., Chen, J., & Liu, Q. (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/cvpr42600.2020.00907 · Cited by 131
Paul, S. G., Saha, A., Hasan, M. Z., Noori, S. R. H., & Moustafa, A. A. (2024) · IEEE Access · doi:10.1109/access.2024.3354809 · Cited by 150
“GNN has emerged as a specialized class of machine learning (ML) models tailored to operate on graph-structured data within the healthcare domain [2], [3], [4].”
BackgroundDangayach, R., Jeong, N., Demirel, E., Uzal, N., Fung, V., & Chen, Y. (2024) · Environmental Science & Technology · doi:10.1021/acs.est.4c08298 · Cited by 126
Shi, Z., Zhang, H., Jin, C., Quan, X., & Yin, Y. (2021) · BMC Bioinformatics · doi:10.1186/s12859-021-04073-z · Cited by 119
Semi-supervised learning and graph neural networks for fake news detection
Benamira, A., Devillers, B., Lesot, E., Ray, A. K., Saadi, M., & Malliaros, F. D. (2019) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1145/3341161.3342958 · Cited by 139
“Initially, GNNs were introduced as an extension of Recurrent Neural Networks (RNNs); GNNs apply recurrent layers to each node with additional local averaging layers [3], [4].”
MethodHOPPITY: LEARNING GRAPH TRANSFORMATIONS TO DETECT AND FIX BUGS IN PROGRAMS
Dinella, E., Dai, H., Li, Z., Naik, M., Song, L., & Wang, K. (2021) · Figshare · doi:10.6084/m9.figshare.14128508 · Cited by 84
Hardware Acceleration of Graph Neural Networks
Auten, A., Tomei, M., & Kumar, R. (2020) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac18072.2020.9218751 · Cited by 141
“One such class of algorithms, Graph Neural Networks (GNNs) [13], has generated particular interest due to their ability to outperform existing techniques in many applications [18], [16].”
BackgroundHierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment
She, D., Lai, Y., Yi, G., & Xu, K. (2021) · 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/cvpr46437.2021.00837 · Cited by 130
“In this section, we provide a brief review of image aesthetics assessment (IAA) methods [3, 7, 42, 47] especially those on preserving image layouts and compositions as well as graph-based representation learning meth-ods [4,13,17,39] that are closely related to our work.”
BackgroundForecasting Network Traffic: A Survey and Tutorial With Open-Source Comparative Evaluation
Ferreira, G. O., Ravazzi, C., Dabbene, F., Calafiore, G. C., & Fiore, M. (2023) · IEEE Access · doi:10.1109/access.2023.3236261 · Cited by 136
“[64], are on the rise and have provided results superior to the aforementioned approaches when dealing with road traffic forecasting problems.”
ResultA Survey on Malware Detection with Graph Representation Learning
Bilot, T., Madhoun, N. E., Agha, K. A., & Zouaoui, A. (2024) · ACM Computing Surveys · doi:10.1145/3664649 · Cited by 151
“Recent graph representation learning approaches tend to be inspired from the Graph Neural Network (GNN) model [68][69], which is the origin of the first application of deep neural networks to graph-structured data.”
BackgroundA review of physics-informed machine learning for building energy modeling
Ma, Z., Jiang, G. Y., Hu, Y., & Chen, J. (2024) · Applied Energy · doi:10.1016/j.apenergy.2024.125169 · Cited by 139
Learning Symbolic Physics with Graph NetworksPreprint
Cranmer, M., Xu, R., Battaglia, P., & Ho, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.05862 · Cited by 123
“The first ingredient in our approach is the “graph network” (GN) [Battaglia et al., 2018], a type of graph neural network [Scarselli et al., 2009, Bronstein et al., 2017, Gilmer et al., 2017], which is effective at learning the dynamics of complex physical systems [Battaglia et al., 2016, Chang et…”
MethodAdvancing pharmaceutical research: A comprehensive review of cutting-edge tools and technologies
Chen, J., Lin, A., & Luo, P. (2024) · Current Pharmaceutical Analysis · doi:10.1016/j.cpan.2024.11.001 · Cited by 112
Network planning with deep reinforcement learning
Zhu, H., Gupta, V., Ahuja, S. S., Tian, Y., Zhang, Y., & Jin, X. (2021) · Proceedings of the 2021 ACM SIGCOMM 2021 Conference · doi:10.1145/3452296.3472902 · Cited by 112
“GNNs are a family of neural networks specifically designed for graph data [78].”
MethodInfluentialDIRE: A Neural Approach to Decompiled Identifier Naming
Lacomis, J., Yin, P., Schwartz, E. J., Allamanis, M., Goues, C. L., Neubig, G., & Vasilescu, B. (2019) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase.2019.00064 · Cited by 168
“For this purpose, we also employ structural encoding of the code using GGNNs, a class of neural models that map graphs to outputs [34], [35].”
MethodLearning to Model Relationships for Zero-Shot Video Classification
Gao, J., Zhang, T., & Xu, C. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2985708 · Cited by 127
Neural Networks-Based Aerodynamic Data Modeling: A Comprehensive Review
Hu, L., Zhang, J., Xiang, Y., & Wang, W. (2020) · IEEE Access · doi:10.1109/access.2020.2993562 · Cited by 119
“Graph neural networks (GNNs) were firstly proposed by Scarselli in 2009 [54].”
SGKT: Session graph-based knowledge tracing for student performance prediction
Wu, Z., Huang, L., Huang, Q., Huang, C., & Tang, Y. Z. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117681 · Cited by 112
Qiao, N., Zhao, Y., Gao, J., Chen, C., Li, X., Li, T., & Yin, M. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad094 · Cited by 112
Deep learning for cybersecurity in smart grids: Review and perspectives
Ruan, J., Liang, G., Zhao, J., Zhao, H. Q., Qiu, J., Wen, F., & Dong, Z. Y. (2023) · Energy Conversion and Economics · doi:10.1049/enc2.12091 · Cited by 123
SiLK: Simple Learned Keypoints
Gleize, P., Wang, W., & Feiszli, M. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02056 · Cited by 133
Abdi, N., Albaseer, A. M., & Abdallah, M. M. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3354045 · Cited by 127
“These embeddings are useful for making predictions at the individual node and graph levels [116].”
BackgroundDrug target prediction through deep learning functional representation of gene signatures
Chen, H., King, F. J., Zhou, B., Wang, Y., Canedy, C. J., Hayashi, J., Zhong, Y., Chang, M. W., Pache, L., Wong, J. L., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-46089-y · Cited by 119
“Therefore, a futuredirection is to scale the FRoGS framework to extract protein-protein interaction (PPI) signals in gene signatures by leveraging graph neural networks 72 , similar to some recent reports 3,29 .”
TrimNet: learning molecular representation from triplet messages for biomedicine
Li, P., Li, Y., Hsieh, C., Zhang, S., Liu, X., Liu, H., Song, S., & Yao, X. (2020) · Briefings in Bioinformatics · doi:10.1093/bib/bbaa266 · Cited by 124
A Comprehensive Review on Vision-Based Violence Detection in Surveillance Videos
Ullah, F. U. M., Obaidat, M. S., Ullah, A., Muhammad, K., Hijji, M., & Baik, S. W. (2023) · ACM Computing Surveys · doi:10.1145/3561971 · Cited by 99
“Consequently, motivations have been obtained from several aspects of these NNs such as CNN [68], RNN [69], deep autoencoder [70], GNN [71], GAN [72], and so on.”
BackgroundFrom statistical relational to neurosymbolic artificial intelligence: A survey
Marra, G., Dumančić, S., Manhaeve, R., & Raedt, L. D. (2024) · Artificial Intelligence · doi:10.1016/j.artint.2023.104062 · Cited by 202
“Link prediction has been one of the key tasks in StarAI [44], and more recently also in NeSy as NeSy allows to merge symbolic reasoning (from StarAI) with the recent geometric deep learning approaches based on Knowledge Graph Embeddings (KGE) [128] and Graph Neural Networks [107].”
MethodREVISED NOTE ON LEARNING QUADRATIC ASSIGNMENT WITH GRAPH NEURAL NETWORKS
Nowak-Vila, A., Villar, S., Bandeira, A. S., & Bruna, J. (2018) · IEEE Data Science Workshop (DSW) · doi:10.1109/dsw.2018.8439919 · Cited by 132
“The Graph Neural Network, introduced in [26] and further simplified in [8, 18, 27] is a neural network architecture based on local operators of a graph G = (V,E), offering a powerful balance between expressivity and sample complexity; see [5] for a recent survey on models and applications of deep learning on graphs.”
BackgroundMethodTeaNet: Universal neural network interatomic potential inspired by iterative electronic relaxations
Takamoto, S., IZUMI, S., & Li, J. (2022) · Computational Materials Science · doi:10.1016/j.commatsci.2022.111280 · Cited by 124
“One can find similarities to the recurrent GCN architecture [10].”
BackgroundHeteroGraphRec: A heterogeneous graph-based neural networks for social recommendations
Salamat, A., Luo, X., & Jafari, A. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.106817 · Cited by 123
Toward Subgraph-Guided Knowledge Graph Question Generation With Graph Neural Networks
Chen, Y., Wu, L., & Zaki, M. J. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3264519 · Cited by 140
“aph. We instead rely on GNNs to encode the KG subgraph, which captures both the node/edge features and graph structures. B. Graph Neural Networks Over the past few years, graph neural networks (GNNs) [18], [19], [20], [21], [22], [23], [24], [25], [26] have attracted increasing attention since they extend traditional…”
BackgroundA Survey of Multi-modal Knowledge Graphs: Technologies and Trends
Liang, W., Meo, P. D., Tang, Y. Z., & Zhu, J. (2024) · ACM Computing Surveys · doi:10.1145/3656579 · Cited by 137
“…types of neural networks commonly used in encoding models include Multilayer Percep-trons ( MLP ) [31], Convolutional Neural Networks ( CNNs ) [8], Recurrent Neural Networks ( RNNs ) [111], Transformers [92], Graph Neural Networks ( GNNs ) [79], and Restricted Boltz-mann Machines ( RBMs ) [64].”
Graph neural networks for text classification: a survey
Wang, K., Ding, Y., & Han, S. C. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10808-0 · Cited by 130
“To tackle the limitation of traditional graph-based algorithms and better represent non-Euclidean relations in practical applications, Graph Neural Networks are proposed by [100].”
Geometric deep learning on graphs and manifolds using mixture model CNNsPreprint
Monti, F., Boscaini, D., Masci, J., Rodolà, E., Svoboda, J., & Bronstein, M. M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.08402 · Cited by 146
“[19, 41].”
Group-Wise Learning for Weakly Supervised Semantic Segmentation
Zhou, T., Li, L., Li, X., Feng, C.-M., Li, J., & Shao, L. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3132834 · Cited by 113
Molecular representations for machine learning applications in chemistry
Raghunathan, S., & Priyakumar, U. D. (2021) · International Journal of Quantum Chemistry · doi:10.1002/qua.26870 · Cited by 122
Николаевна, П. Е., Maximenko, V. A., Kurkin, S., Sergeev, A., Stoyanov, D., Paunova, R., Kandilarova, S., Simeonova, D., & Hramov, A. E. (2023) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2022.113041 · Cited by 115
Deep Learning Models for PV Power Forecasting: Review
Yu, J., Li, X., Yang, L., Li, L., Huang, Z., Shen, K., Xu, Y., Xu, Y., Xu, Z., Zhang, D., et al. (2024) · Energies · doi:10.3390/en17163973 · Cited by 125
“Various robust model architectures, such as multilayer perceptrons (MLP) [3], recurrent neural networks (RNN) [4], convolutional neural networks (CNN) [5], and graph neural networks (GNN) [6] have been applied to PV power forecasting.”
A Generalization of Convolutional Neural Networks to Graph-Structured DataPreprint
Hechtlinger, Y., Chakravarti, P., & Qin, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.08165 · Cited by 120
“The earliest work in the field is the Graph Neural Network by Scarselli and others, starting with Gori et al. (2005) and fully presented in Scarselli et al. (2009).”
BackgroundLabeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation LearningPreprint
Zhang, M., Li, P., Xia, Y., Wang, K., & Jin, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.16103 · Cited by 285
Pre-training via Denoising for Molecular Property PredictionPreprint
Zaidi, S., Schaarschmidt, M., Martens, J., Kim, H., Teh, Y., Sanchez-Gonzalez, A., Battaglia, P., Pascanu, R., & Godwin, J. (2022) · International Conference on Learning Representations · doi:10.48550/arxiv.2206.00133 · Cited by 177
“Specific to GNNs (Battaglia et al., 2018; Scarselli et al., 2009; Bronstein et al., 2017), randomizing input graph features has been shown to improve performance (Hu et al., 2020a; Sato et al., 2021).”
BackgroundInfluentialRabin, M. R. I., Bui, N. D. Q., Wang, K., Yu, Y., Jiang, L., & Alipour, M. A. (2021) · Information and Software Technology · doi:10.1016/j.infsof.2021.106552 · Cited by 142
“As Graph Neural Networks (GNN) [43] have been gaining increasing popularity due to its remarkable representation capacity, many works have leveraged GNN to tackle challenging tasks like program repair and bug finding, and obtained quite promising results [4, 53, 17, 34, 12, 17, 47].”
BackgroundUnreliable Users Detection in Social Media: Deep Learning Techniques for Automatic Detection
Sansonetti, G., Gasparetti, F., D’Aniello, G., & Micarelli, A. (2020) · IEEE Access · doi:10.1109/access.2020.3040604 · Cited by 119
“Several promising fake news detection approaches based on Graph Neural Networks (GNNs) [22], [23] have recently been proposed, motivated by the latest developments in the domain [24], [25].”
BackgroundLearning Feature Recovery Transformer for Occluded Person Re-Identification
Xu, B., He, L., Liang, J., & Sun, Z. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3186759 · Cited by 119
“Graph Convolutional Networks (GCN) is firstly proposed in [35] to build the relationship between graph nodes, and has been proved to be effective in many computer vision tasks [36]–[38].”
BackgroundRelational inductive bias for physical construction in humans and machines
Hamrick, J. B., Allen, K. R., Bapst, V., Zhu, T., McKee, K. R., Tenenbaum, J. B., & Battaglia, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.01203 · Cited by 61
“We instantiate a relational inductive bias in a deep RL agent via a “graph network”, a neural network for relational reasoning whose relatives (Scarselli et al., 2009) have proven effective in theoretical computer science (Dai et al., 2017), quantum chemistry (Gilmer et al., 2017), robotic control…”
BackgroundMethodBertGCN: Transductive Text Classification by Combining GCN and BERTPreprint
Lin, Y., Meng, Y., Sun, X., Han, Q., Kuang, K., Li, J., & Wu, F. Q. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.05727 · Cited by 130
“Graph neural networks (GNNs) are connectionist models that capture dependencies and relations between graph nodes via message passing through edges that connect nodes (Scarselli et al., 2008; Hamilton et al., 2017; Xu et al., 2018).”
BackgroundGophormer: Ego-Graph Transformer for Node ClassificationPreprint
Zhao, J., Li, C., Wen, Q., Wang, Y., Liu, Y., Sun, H., Xie, X., & Ye, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.13094 · Cited by 131
Gravity-Inspired Graph Autoencoders for Directed Link Prediction
Salha-Galvan, G., Limnios, S., Hennequin, R., Tran, V.-A., & Vazirgiannis, M. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3358023 · Cited by 124
“g neighborhood structure and node proximity, are notorious examples of such similarity indices. More recently, along with the increasing efforts in extending Deep Learning methods to graph structures [6, 43, 54], these approaches have been outperformed by the node embedding paradigm [16, 46, 56]. In a nutshell, the st…”
MethodNikolentzos, G., Dasoulas, G., & Vazirgiannis, M. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.07.008 · Cited by 153
Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
Oono, K., & Suzuki, T. (2020) · International Conference on Learning Representations · Cited by 589
Deep graph similarity learning: a survey
Ma, G., Ahmed, N. K., Willke, T. L., & Yu, P. S. (2021) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-020-00733-5 · Cited by 95
Ma, Y., & Tang, J. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108924184 · Cited by 94
Protein Docking Model Evaluation by Graph Neural Networks
Wang, X., Flannery, S. T., & Kihara, D. (2021) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2021.647915 · Cited by 103
“In this work, we address this limitation of DOVE by applying a graph neural network (GNN)( 35, 36 ), which has previously been successful in representing molecular properties ( 37-40 ).”
MethodScenario Understanding and Motion Prediction for Autonomous Vehicles—Review and Comparison
Karle, P., Geisslinger, M., Betz, J., & Lienkamp, M. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3156011 · Cited by 126
“The usage of Graph Neural Network (GNN) [147], [148] for motion prediction is shown by Gao et al. [149].”
MethodDropKey for Vision Transformer
Li, B., Hu, Y., Nie, X., Han, C., Jiang, X., Guo, T., & Liu, L. (2023) · 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/cvpr52729.2023.02174 · Cited by 137
Diverse Generation for Multi-Agent Sports Games
Yeh, R. A., Schwing, A. G., Huang, J., & Murphy, K. P. (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.2019.00474 · Cited by 143
“Graph neural networks: To model interactions between variables, graph neural networks (GNN) [33] have been proposed.”
MethodA Behavioral Approach to Visual Navigation with Graph Localization Networks
Chen, K., Pablo de Vicente, J., Sepulveda, G., Xia, F., Soto, A., Vzquez, M., & Savarese, S. (2019) · Robotics: Science and Systems XV · doi:10.15607/rss.2019.xv.010 · Cited by 86
Adaptive Propagation Graph Convolutional Network
Spinelli, I., Scardapane, S., & Uncini, A. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3025110 · Cited by 124
Pixel2Mesh: 3D Mesh Model Generation via Image Guided Deformation
Wang, N., Zhang, Y., Li, Z., Fu, Y., Yu, H., Liu, W., Xue, X., & Jiang, Y. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2984232 · Cited by 118
“Our base network is a graph neural network [31]; this architecture has been adopted for shape analysis [32].”
MethodHigher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks
Li, J., Peng, H. M., Cao, Y., Dou, Y., Zhang, H., Yu, P. S., & He, L. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3074654 · Cited by 139
“GNNs, introduced by [22], [23], are extended from recursive neural networks so as to operate on graph-structured data.”
BackgroundExploring Radar Data Representations in Autonomous Driving: A Comprehensive Review
Yao, S., Guan, R., Peng, Z., Xu, C., Shi, Y., Ding, W., Lim, E. G., Yue, Y., Seo, H., Man, K. L., et al. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3554781 · Cited by 125
“…from the radar data, potentially improving the accuracy and efficiency of parameter extraction. b) Feature Extraction: Graph Neural Networks (GNNs) [219] present a promising research direction, enabling operations on graph data to effectively capture relationships between elements within complex…”
Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation
Ghosh, P., Yao, Y., Davis, L. S., & Divakaran, A. (2020) · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv45572.2020.9093361 · Cited by 88
“GNNs have been used in a number of different applications like situation recognition [24], human-object interaction [25], webpage ranking[39, 40], mutagenesis[39], etc.”
BackgroundMethodSong, X., Mao, M., & Qian, X. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3053568 · Cited by 100
Chen, J., Li, K., Li, K., Yu, P. S., & Zeng, Z. (2021) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3446342 · Cited by 114
“Graph Neural Network (GNN) is an effective deep learning model used in graph or network applications [5, 18, 25, 28].”
BackgroundMethodPeng, W., Hu, Y. H., Xing, L., Xie, Y., Sun, Y., & Li, Y. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/600 · Cited by 148
Artificial Intelligence for Retrosynthesis Prediction
Jiang, Y., Yu, Y., Kong, M. C., Mei, Y., Yuan, L., Huang, Z., Kuang, K., Wang, Z., Yao, H., Zou, J., et al. (2022) · Engineering · doi:10.1016/j.eng.2022.04.021 · Cited by 125
“Researchers have also proposed recurrent graph neural networks (RecGNNs), in which the neighbour information iteratively propagates to update the representation of the target node [33,34].”
BackgroundAI-Driven Inverse Design of Materials: Past, Present, and Future
Han, X., Wang, X.-D., 徐, M.-Y. 孟. X., Zhen, F., 姚, B.-W. 博. Y., Guo, P.-J., Gao, Z.-F., & Lu, Z.-Y. (2025) · Chinese Physics Letters · doi:10.1088/0256-307x/42/2/027403 · Cited by 123
Modelling urban-scale occupant behaviour, mobility, and energy in buildings: A survey
Salim, F. D., Dong, B., Ouf, M. M., Wang, Q., Pigliautile, I., Kang, X., Hong, T., Wu, W., Liu, Y., Rumi, S. K., et al. (2020) · Building and Environment · doi:10.1016/j.buildenv.2020.106964 · Cited by 112
“Graph Neural Network (GNN) [266] Traffic, optimization problem and biology”
BackgroundLGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment
Liang, Q., Li, Z., Cheng, Z., Zhang, P., Pu, S., Niu, Y., Ren, W., Tan, W., & Wu, F. Q. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86549-8_7 · Cited by 104
GrabPhisher: Phishing Scams Detection in Ethereum via Temporally Evolving GNNs
Zhang, J., Sui, H., Sun, X., Ge, C., Zhou, L. Q., & Susilo, W. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3411449 · Cited by 117
Tree2Vector: Learning a Vectorial Representation for Tree-Structured Data
Zhang, H., Wang, S., Xu, X., Chow, T. W. S., & Wu, Q. M. J. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2797060 · Cited by 108
“networks (GNNs) [46], which extend multilayer perceptron into the domain of graphs (cyclic and acyclic), and recursive neural networks (RNNs) [47], with an input domain consisting of directed acyclic graphs, which are mapped into vectors of reals.”
Influential
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.