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 901–1,000 of 1,052
Graph Attention Networks for Anti-Spoofing
Tak, H., Jung, J.-W., Patino, J., Todisco, M., & Evans, N. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-993 · Cited by 79
Quantum Neural Network for Quantum Neural Computing
Zhou, M.-G., Liu, Z.-P., Yin, H.-L., Li, C.-L., Xu, T.-K., & Chen, Z.-B. (2023) · Research · doi:10.34133/research.0134 · Cited by 79
A Joint 3D UNet-Graph Neural Network-Based Method for Airway Segmentation from Chest CTs
Juárez, A. G.-U., Selvan, R., Saghir, Z., & de Bruijne, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32692-0_67 · Cited by 79
Fast Haar Transforms for Graph Neural Networks
Li, M., Ma, Z., Wang, Y. G., & Zhuang, X. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.04.028 · Cited by 87
Composition-Aware Image Aesthetics Assessment
Liu, D., Puri, R., Kamath, N., & Bhattacharya, S. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093412 · Cited by 95
“With the graph representation, we apply the Graph Convolution operations to perform reasoning.”
InfluentialMultivariate Time Series Forecasting with Transfer Entropy Graph
Duan, Z., Xu, H., Huang, Y., Feng, J. M., & Wang, Y. (2022) · Tsinghua Science & Technology · doi:10.26599/tst.2021.9010081 · Cited by 83
“The concept of graph neural network (GNN) was first proposed in [24], which extended existing neural networks for processing the data represented in graph domains.”
BackgroundZhao, X., Jia, M., Ding, P., Yang, C., She, D., & Liu, Z. (2020) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2020.3004589 · Cited by 83
“Currently, the continuous emergence of graph embedding and graph neural networks algorithms [31] provides a new research idea for the development of DELM algorithm.”
BackgroundMethodIs Machine Learning Ready for Traffic Engineering Optimization?
Bernárdez, G., Suárez‐Varela, J., López, A. V., Wu, B., Xiao, S., Cheng, X., Barlet‐Ros, P., & Cabellos‐Aparicio, A. (2021) · IEEE International Conference on Network Protocols (ICNP) · doi:10.1109/icnp52444.2021.9651930 · Cited by 79
Wu, J., Li, B., Qin, Y., Ni, W., Zhang, H., Fu, R., & Sun, Y. (2021) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2021.102615 · Cited by 95
A newcomer’s guide to deep learning for inverse design in nano‐photonics
Khaireh-Walieh, A., Langevin, D., Bennet, P., Teytaud, O., Moreau, A., & Wiecha, P. R. (2023) · Nanophotonics · doi:10.1515/nanoph-2023-0527 · Cited by 94
Rethinking pooling in graph neural networksPreprint
Mesquita, D. P. P., Junior, A. H. D. S., & Kaski, S. (2020) · Aaltodoc (Aalto University) · doi:10.48550/arxiv.2010.11418 · Cited by 156
“The success of graph neural networks (GNNs) [3, 36] in many domains [9, 15, 25, 41, 46, 50] is due to their ability to extract meaningful representations from graph-structured data.”
BackgroundNakashima, K., Kamiya, S., Ohtsu, K., Yamamoto, K., Nishio, T., & Morikura, M. (2019) · IEEE Access · doi:10.1109/access.2020.2973140 · Cited by 90
“To extract the features of the adjacent APs and used channels, we propose incorporating graph convolutional layers [18]–[21] into a neural network.”
BackgroundMethodGraph Representations for Higher-Order Logic and Theorem Proving
Paliwal, A., Loos, S., Rabe, M., Bansal, K., & Szegedy, C. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i03.5689 · Cited by 68
Kieseler, J. (2020) · The European Physical Journal C · doi:10.1140/epjc/s10052-020-08461-2 · Cited by 93
“thermore, there is a trend towards employing such algorithms for more tasks in high energy physics further towards the beginning of the reconstruction sequence. In this context, graph neural networks [26] are receiving increasing attention because they allow to directly process detector inputs or particles, which are…”
BackgroundPersonalized DeepInf: Enhanced Social Influence Prediction with Deep Learning and Transfer Learning
Leung, C. K.-S., Cuzzocrea, A., Mai, J. J., Deng, D., & Jiang, F. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9005969 · Cited by 86
“We observed that SIA in deep learning can be considered as a GNN [34] related problem.”
BackgroundContinuous-Time Link Prediction via Temporal Dependent Graph Neural Network
Qu, L., Zhu, H., Duan, Q., & Shi, Y. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366423.3380073 · Cited by 97
“As for the latter, built on the success of deep learning [19] techniques operating on regular Euclidean structural data such as images [5] and texts [4], GNN [28] and Graph Convolutional Network (GCN) [17] are proposed to operate on irregular non-Euclidean structural network/graph data.”
BackgroundAutonomous Exploration Under Uncertainty via Deep Reinforcement Learning on Graphs
Chen, F., Martin, J. D., Huang, Y., Wang, J., & Englot, B. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341657 · Cited by 103
“GNNs incorporate graphs into neural network models, permitting a variety of queries to be posed over them [14].”
BackgroundMutual CRF-GNN for Few-shot Learning
Tang, S., Chen, D., Bai, L., Liu, K., Ge, Y., & Ouyang, W. (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/cvpr46437.2021.00236 · Cited by 82
“Recently, Graph Neural Network (GNN) [60, 31] becomes a rising method to transfer the knowledge from the †This work was done when Shixiang Tang was an intern at SenseTime. support samples to the query samples.”
MethodBlock Modeling-Guided Graph Convolutional Neural Networks
He, D., Liang, C., Liu, H., Wen, M., Jiao, P., & Feng, Z. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i4.20319 · Cited by 109
A Comparison of Machine Learning Approaches for Predicting Employee Attrition
Guerranti, F., & Dimitri, G. M. (2022) · Applied Sciences · doi:10.3390/app13010267 · Cited by 92
“Furthermore, we plan to use more advanced deep learning methods, such as graph neural networks (GNNs) [31,32], to handle interactions between employees based on the hypothesis of homophily, that is, employees who are “ closer ” to each other are more likely to behave similarly.”
MethodReview of Deep Reinforcement Learning and Its Application in Modern Renewable Power System Control
Li, Q., Lin, T., Yu, Q., Du, H. L., Li, J., & Fu, X. (2023) · Energies · doi:10.3390/en16104143 · Cited by 86
Graph neural networks for construction applications
Jia, Y., Wang, J., Shou, W., Hosseini, M. R., & Bai, Y. (2023) · Automation in Construction · doi:10.1016/j.autcon.2023.104984 · Cited by 87
From Graph Theory to Graph Neural Networks (GNNs): The Opportunities of GNNs in Power Electronics
Li, Y., Xue, C., Zargari, F., & Li, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3345795 · Cited by 90
“Founded on an information diffusion mechanism, the core difference of GNNs over conventional graph representation learning lies in how topological information is encoded during the learning process [93], [94].”
BackgroundDA-GNN: A smart contract vulnerability detection method based on Dual Attention Graph Neural Network
Zhen, Z., Zhao, X., Zhang, J., Wang, Y., & Chen, H. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110238 · Cited by 82
StructGNN: An efficient graph neural network framework for static structural analysis
Chou, Y., Chang, W.-T., Jean, J. G., Chang, K.-H., Huang, Y., & Chen, C. (2024) · Computers & Structures · doi:10.1016/j.compstruc.2024.107385 · Cited by 91
Olivetti, L., & Messori, G. (2024) · Geoscientific model development · doi:10.5194/gmd-17-7915-2024 · Cited by 96
A Comprehensive Review of Deep Learning Applications with Multi-Omics Data in Cancer Research
Sartori, F., Codicè, F., Caranzano, I., Rollo, C., Birolo, G., Fariselli, P., & Pancotti, C. (2025) · Genes · doi:10.3390/genes16060648 · Cited by 85
“Techniques such as convolutional neural networks (CNNs) [13], graph neural networks (GNNs) [14], recurrent neural networks (RNNs) [15], and Transformer-based networks [16] have revolutionized multi-omics data integration and interpretation.”
Sequential Graph Neural Network for Urban Road Traffic Speed Prediction
Xie, Z., Lv, W., Huang, S., Lu, Z., Du, B., & Huang, R. (2019) · IEEE Access · doi:10.1109/access.2019.2915364 · Cited by 88
“For example, the GNN model proposed by Scarselli et al. [17] can map a graph G and all its nodes n ∈ N into an m -dimensional Euclidean space, while Li et al. [18] extended the work of [17] using gated recurrent units to form GNN output sequences.”
MethodGraph Neural Solver for Power Systems
Donon, B., Donnot, B., Guyon, I., & Marot, A. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8851855 · Cited by 105
“This class of artificial neural networks was first introduced by F. Scarselli in [28] and further developed in [22] and [14].”
BackgroundDWIE: An entity-centric dataset for multi-task document-level information extraction
Zaporojets, K., Deleu, J., Develder, C., & Demeester, T. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2021.102563 · Cited by 110
Runtime Performance Prediction for Deep Learning Models with Graph Neural Network
Gao, Y., Gu, X., Zhang, H., Lin, H., & Yang, M. (2023) · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1109/icse-seip58684.2023.00039 · Cited by 97
“In this paper, we propose DNNPerf, a novel ML-based tool for predicting the runtime performance of DL models with Graph Neural Network (GNN) [21].”
BackgroundMethodHashmi, K. A., Liwicki, M., Stricker, D., Afzal, M. A., Afzal, M. A., & Afzal, M. Z. (2021) · IEEE Access · doi:10.1109/access.2021.3087865 · Cited by 85
“[96] exploited the graph neural networks [97] to perform table recognition”
BackgroundWu, N., Xie, Y., & Hao, C. (2022) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2022.3185540 · Cited by 99
“…DFGs. 2) GPP is a GNN-based performance predictor, which estimates post-implementation resource usage and timing of DFGs. GNNs [29], [40], [41] are adopted for three reasons: a) DFGs are graphs, which are naturally suitable for GNNs to learn the underlying information from graph…”
BackgroundDeep Graph Memory Networks for Forgetting-Robust Knowledge Tracing
Abdelrahman, G. M., & Wang, Q. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3206447 · Cited by 109
“[35] proposed a graph neural networkmodel that candistill information froman input graph to perform supervised learning tasks.”
BackgroundA multivariate time series graph neural network for district heat load forecasting
Wang, Z., Liu, X., Huang, Y., Zhang, P., & Fu, Y. (2023) · Energy · doi:10.1016/j.energy.2023.127911 · Cited by 77
“Graph neural networks (GNNs) are a class of deep learning models that can learn from graph-structured data, such as molecules, knowledge and social networks [14].”
BackgroundLearning characteristics of graph neural networks predicting protein–ligand affinities
Mastropietro, A., Pasculli, G., & Bajorath, J. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00756-9 · Cited by 85
“Furthermore, GNNs 19,20 including message-passing NNs (MPNNs) 21 have increasingly been used for the prediction of affinity from protein–ligand interaction graphs, which are usually obtained from X-ray structures of protein–ligand complexes.”
Multilayer network simplification: Approaches, models and methods
Interdonato, R., Magnani, M., Perna, D., Tagarelli, A., & Vega, D. (2020) · Computer Science Review · doi:10.1016/j.cosrev.2020.100246 · Cited by 94
Probabilistic symmetries and invariant neural networksPreprint
Bloem-Reddy, B., & Teh, Y. W. (2019) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.48550/arxiv.1901.06082 · Cited by 194
“, 2016), and graph neural networks (Scarselli et al., 2009) are a few recent examples from the rapidly expanding literature.”
Looking to Relations for Future Trajectory Forecast
Choi, C., & Dariush, B. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00101 · Cited by 79
“Relational inference has been presented in [28, 17] to reason the implications of relations over graph structured data.”
BackgroundDeep learning in target prediction and drug repositioning: Recent advances and challenges
Yu, J., Dai, Q.-Q., & Li, G. (2021) · Drug Discovery Today · doi:10.1016/j.drudis.2021.10.010 · Cited by 82
A review of Graph Neural Networks for Electroencephalography data analysis
Graña, M., & Morais-Quilez, I. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126901 · Cited by 84
Wang, C., & Liu, G. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102357 · Cited by 81
Dynamic Heterogeneous Graph Neural Network for Real-time Event Prediction
Luo, W., Zhang, H., Yang, X., Bo, L., Yang, X., Li, Z., Qie, X., & Ye, J. (2020) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3394486.3403373 · Cited by 90
“Graph Neural Network Method GNNs [22] have gained a lot of attention in recent years.”
BackgroundPredicting emerging drug interactions using GNNs
Le, N. Q. K. (2023) · Nature Computational Science · doi:10.1038/s43588-023-00555-7 · Cited by 78
Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis
Liu, J., Cen, X., Yi, C., Wang, F.-A., Ding, J., Cheng, J., Wu, Q., Gai, B., Zhou, Y., He, R., et al. (2025) · Genomics, Proteomics & Bioinformatics · doi:10.1093/gpbjnl/qzaf011 · Cited by 75
“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] (Figure 2C).”
Shan, X., Cao, J., Huo, S., Chen, L., Sarrigiannis, P. G., & Zhao, Y. (2022) · Human Brain Mapping · doi:10.1002/hbm.25994 · Cited by 75
“In 1997, Sperduti and Starita first adopted neural networks to direct acyclic graphs (Sperduti & Starita, 1997), which motivated the early studies on GCNs (Gallicchio & Micheli, 2010; Gori et al., 2005; Scarselli et al., 2008).”
BackgroundKnowledge Graph Embeddings and Explainable AI
Bianchi, F., Rossiello, G., Luca, C., Palmonari, M., & Minervini, P. (2020) · Studies on the semantic web · doi:10.3233/ssw200011 · Cited by 101
“KG embedding models are in general shallow and linear models and should be distinguished from GNNs [78], which are neural networks that take relational structures as inputs.”
BackgroundBeyond Short-Term Snippet: Video Relation Detection With Spatio-Temporal Global Context
Liu, C., Yang, J., Xu, K., Gong, G., & Mu, Y. (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/cvpr42600.2020.01085 · Cited by 91
“Graph Neural Networks Graph Neural Networks (GNNs) [12, 32] is widely applied to process graph data, propagating neighboring information among elements in the graph.”
BackgroundEvaluating Attribution for Graph Neural Networks
Sánchez-Lengeling, B., Wei, J. N., Lee, B. K., Reif, E., Wang, P. Y., Qian, W. W., McCloskey, K., Colwell, L. J., & Wiltschko, A. B. (2020) · neural information processing systems · Cited by 206
The Surprising Performance of Simple Baselines for Misinformation Detection
Pelrine, K., Danovitch, J., & Rabbany, R. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3450111 · Cited by 98
“• Han et al. [28] use a GNN [76] to encode the propagation network and features of the users in it (not including text).”
MethodHu, X., Feng, C., Zhou, Y., Harrison, A., & Chen, M. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btab737 · Cited by 65
Hyperspectral Image Classification Using Feature Fusion Hypergraph Convolution Neural Network
Ma, Z., Jiang, Z., & Zhang, H. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3123423 · Cited by 75
“Graph neural network (GNN) was first proposed in [32], and then various models have been gradually developed, such as graph convolution network [33], graph attention network [34], GraphSAGE (SAmple and aggreGatE) [35], etc.”
An end-to-end approach to segmentation in medical images with CNN and posterior-CRF
Chen, S., Gamechi, Z. S., Dubost, F., van Tulder, G., & de Bruijne, M. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102311 · Cited by 84
Deep Graph Learning for Anomalous Citation Detection
Liu, J., Xia, F., Xu, F., Ren, J. F., & Liu, H. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3145092 · Cited by 87
Alaoui, D. E., Riffi, J., Sabri, M. A., Aghoutane, B., Yahyaouy, A., & Tairi, H. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07059-x · Cited by 80
“The recommender system studies have given a lot of attention since years graph neural network (GNN) [38] technologies as many fields (financial markets, search engines, social network analysis, computational chemistry, image and voice recognition, etc.”
BackgroundNetwork-based approaches for modeling disease regulation and progression
Galindez, G., Sadegh, S., Baumbach, J., Kacprowski, T., & List, M. (2023) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2022.12.022 · Cited by 79
ZeroBind: a protein-specific zero-shot predictor with subgraph matching for drug-target interactions
Wang, Y., Xia, Y., Yan, J., Yuan, Y., Shen, H., & Pan, X. (2023) · Nature Communications · doi:10.1038/s41467-023-43597-1 · Cited by 80
Feng, B., Shi, J., Huang, L., Yang, Z., Feng, S., Li, J., Chen, Q., Xue, H., Chen, X., Wan, C., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-44946-4 · Cited by 83
“Based on the acquired local model relationship matrix, graph convolutional networks (GCNs) 34 were employed to generate an adjacency matrix.”
MethodPrivacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses
Fang, H., Qiu, Y., Yu, H., Yu, W., Kong, J., Chong, B., Chen, B., Wang, X., Xia, S., & Xu, K. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-03049-x · Cited by 77
“Graph Neural Networks (GNNs) [115–119] exhibit remarkable efficacy in processing complex graph-structured data and have achieved superior performance in non-Euclidean domains.”
Two-stream spatio-temporal GCN-transformer networks for skeleton-based action recognition
Chen, D., Chen, M., Wu, P., Wu, M., Zhang, T., & Li, C. (2025) · Scientific Reports · doi:10.1038/s41598-025-87752-8 · Cited by 84
Learning a Large Neighborhood Search Algorithm for Mixed Integer ProgramsPreprint
Sonnerat, N., Wang, P., Ktena, S. I., Bartunov, S., & Nair, V. B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.10201 · Cited by 75
“Network architecture: We use a Graph Convolutional Network (Battaglia et al. 2018; Gori, Monfardini, and Scarselli 2005; Scarselli et al. 2008; Hamilton, Ying, and Leskovec 2017; Kipf and Welling 2016) to represent the policy.”
MethodInfluentialChang, L., & Branco, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.13597 · Cited by 94
“Recently, graph neural networks (GNNs) [19] have achieved state-of-the-art performance in cybersecurity tasks, such as network intrusion and anomaly detection [9].”
BackgroundSimple GNN Regularisation for 3D Molecular Property Prediction & BeyondPreprint
Godwin, J., Schaarschmidt, M., Gaunt, A. L., Sánchez‐González, Á., Rubanova, Y., Veličković, P., Kirkpatrick, J., & Battaglia, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.07971 · Cited by 126
“Graph Neural Networks (GNNs) are a family of neural networks that operate on graph structured data by iteratively passing learned messages over the graph’s structure (Scarselli et al., 2009; Bronstein et al., 2017; Gilmer et al., 2017; Battaglia et al., 2018; Shlomi et al., 2021).”
BackgroundAdversarial Label-Flipping Attack and Defense for Graph Neural Networks
Zhang, M., Hu, L., Shi, C., & Wang, X. (2020) · 2020 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm50108.2020.00088 · Cited by 74
“Graph neural networks (GNNs) [23] on graph structured data have shown outstanding results in various tasks such as node classification [3], [5], link prediction [24], graph clustering [25].”
BackgroundGraph Neural Networks for IceCube Signal Classification
Choma, N., Bruna, J., Monti, F., Gerhardt, L., Palczewski, T., Ronaghi, Z., Prabhat, P., Bhimji, W., Bronstein, M. M., & Klein, S. R. (2018) · 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) · doi:10.1109/icmla.2018.00064 · Cited by 65
Deep Graph Convolutional Encoders for Structured Data to Text Generation
Marcheggiani, D., & Perez-Beltrachini, L. (2018) · International Conference on Natural Language Generation · doi:10.18653/v1/w18-6501 · Cited by 156
“GCNs are a variant of graph neural networks (Scarselli et al., 2009) that has been recently proposed by Kipf and Welling (2016).”
BackgroundUnveiling CP property of top-Higgs coupling with graph neural networks at the LHC
Ren, J., Wu, L., & Yang, J. M. (2020) · Physics Letters B · doi:10.1016/j.physletb.2020.135198 · Cited by 74
A Review on Deep Learning Approaches for 3D Data Representations in Retrieval and Classifications
Gezawa, A. S., Zhang, Y., Wang, Q., & Lei, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2982196 · Cited by 81
“The graph spatial filtering idea was first used in [171].”
MethodCui, F., Cui, Q., & Song, Y. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2985588 · Cited by 80
“In recent years, graph neural network [78]–[80] can combine end-to-end learning with inductive reasoning, which is expected to solve the problem that DL cannot reasoning.”
BackgroundMulti-level graph neural network for text sentiment analysis
Liao, W., Zeng, B., Liu, J., Wei, P., Cheng, X., & Zhang, W. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107096 · Cited by 74
Jin, C., Shi, Z., Lin, K. Y., & Zhang, H. (2022) · Biomolecules · doi:10.3390/biom12010064 · Cited by 80
“Graph Neural Networks (GNN) [39] have been proposed in deep learning on graphs.”
BackgroundInfluentialDeep Learning in Diverse Intelligent Sensor Based Systems
Zhu, Y., Wang, M., Yin, X., Zhang, J., Meijering, E. H. W., & Hu, J. (2022) · Sensors · doi:10.3390/s23010062 · Cited by 84
Hierarchical Fuzzy Topological System for High-Dimensional Data Regression Problems
Yao, M., Zhao, T., Cao, J., & Li, J. (2025) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2025.3549791 · Cited by 74
“Initially introduced by Scarselli et al. [17] in 2008, GNNs represent a significant extension of traditional neural networks, enabling the effective processing and analysis of data embedded in graph structures.”
Graph Characterization via Ihara Coefficients
Ren, P., Wilson, R. C., & Hancock, E. R. (2010) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2010.2091969 · Cited by 74
“The application of graphs can be found both in the representation for realworld structured data such as world wide webs [1] and in the description of theories such as neural networks [2], [3].”
GEOMetrics: Exploiting Geometric Structure for Graph-Encoded ObjectsPreprint
Smith, E. J., Fujimoto, S., Romero, A., & Meger, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.11461 · Cited by 88
“Early attempts to extend neural networks to deal with arbi-1 trarily structured graphs relied on recursive neural networks (Frasconi et al., 1998; Gori et al., 2005; Scarselli et al., 2009).”
BackgroundMeshGAN: Non-linear 3D Morphable Models of FacesPreprint
Cheng, S., Bronstein, M. M., Zhou, Y., Kotsia, I., Pantić, M., & Zafeiriou, S. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.10384 · Cited by 88
“First formulations of neural networks on graphs [28, 58] preceding the recent renaissance of deep learning, constructed learnable information diffusion processes.”
BackgroundLearning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
Pathak, D., Lu, C., Darrell, T. J., Isola, P., & Efros, A. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.05546 · Cited by 57
“In this work, we represent the agent’s policy via a graph neural network [17] in such a way that it explicitly corresponds to the morphology of the agent.”
BackgroundMethodLei, B., Li, Y., Fu, W., Yang, P., Chen, S., Wang, T., Xiao, X., Niu, T., Fu, Y., Wang, S., et al. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103213 · Cited by 73
“…among non-Euclidean data, graph-based methods are widely used for disease diagnosis and prediction, such as Graph Neural Network (GNN) (Scarselli et al., 2008), Graph Convolutional Network (GCN) (Welling and Kipf, 2016), Graph Attention Network (GAT) (Velickovic et al., 2017), as well…”
Learning Multi-Attention Context Graph for Group-Based Re-Identification
Yan, Y., Qin, J., Ni, B., Chen, J., Liu, L., Zhu, F., Zheng, W., Yang, X., & Shao, L. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3032542 · Cited by 81
“Second, node features in the group can benefit from the context information through the use of Graph Neural Networks (GNNs), which greatly facilitate information propagation through graph edges.”
BackgroundInfluentialGraph Few-shot Learning with Attribute Matching
Wang, N., Luo, M., Ding, K., Zhang, L., Li, J., & Zheng, Q. (2020) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3340531.3411923 · Cited by 105
“Among various existing learning algorithms for graph data, graph neural networks (GNNs) have achieved superior learning performance in diverse settings [4, 9, 10, 20, 27, 49], which extend the traditional convolution operations [29, 30] for grid data to the non-Euclidean domain [19, 39].”
BackgroundGraph Complemented Latent Representation for Few-Shot Image Classification
Zhong, X., Gu, C., Ye, M., Huang, W., & Lin, C. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3141886 · Cited by 77
“As a learnable recurrent message-passer, where the fixed points could be adjusted discriminatively, GNN is first mentioned in [54] and [55].”
BackgroundBearing fault diagnosis method based on a multi-head graph attention network
Jiang, L., Li, X., Wu, L., & Li, Y. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/ac56f1 · Cited by 75
“In graph structure, nodes are defined by their own characteristics and the characteristics of connected nodes [28].”
Lopera, D. S., Servadei, L., Kiprit, G. N., Wille, R., & Ecker, W. (2023) · ACM Transactions on Design Automation of Electronic Systems · doi:10.1145/3543853 · Cited by 84
“In [50], the proposed architecture is an RNN where the connections between the neurons are classiied into internal and external connections.”
BackgroundEslamlou, A. D., & Huang, S. (2022) · Buildings · doi:10.3390/buildings12122067 · Cited by 83
Graph Lifelong Learning: A Survey
Febrinanto, F. G., Xia, F., Moore, K., Thapa, C., & Aggarwal, C. C. (2023) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2022.3222049 · Cited by 106
“Some baselines can be used, such as GNN with a retraining process as the upper bound and GNNs with incremental scenarios like finetuning as the lower bound.”
InfluentialA Survey on Hyperlink Prediction
Chen, C., & Liu, Y. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3286280 · Cited by 94
“Then, the refined embedding of v i through a GCN layer is given by where N (v i ) denotes the neighbor set of node v i in the expanded graph, σ is a nonlinear activation function, and W conv1 and W conv2 are learnable parameters in the GCN [63].”
BackgroundA Comprehensive Survey on Distributed Training of Graph Neural Networks
Lin, H., Yan, M., Ye, X., Fan, D., Pan, S., Chen, W., & Xie, Y. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3337442 · Cited by 88
“Currently, there is a continuous emergence of techniques addressing performance deterioration in GNNs [70], [72], [73], [138], [139], encouraging the exploration of deeper layer structures in GNN architectures.”
BackgroundGraph Neural Networks in Cancer and Oncology Research: Emerging and Future Trends
Gogoshin, G., & Rodin, A. S. (2023) · Cancers · doi:10.3390/cancers15245858 · Cited by 83
Improving Question Answering by Commonsense-Based Pre-training
Zhong, W., Tang, D., Duan, N., Zhou, M., Wang, J., & Yin, J. P. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32233-5_2 · Cited by 86
Bi, Y., Song, L., Yao, M., Wu, Z., Wang, J., & Xiao, J. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401426 · Cited by 89
“9, 31] aggregate neighbor information by neural network based method. HetGNN [31] jointly learn heterogeneous graph information and heterogeneous contents information for node embeddings based on GNN [23]. Inspired by graph attention networks, R-GCNs [24] are developed to deal with the highly multi-relational data. HA…”
MethodHierarchical Graph Attention Network for Visual Relationship Detection
Li, M., & Chen, Z. (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/cvpr42600.2020.01390 · Cited by 83
“[28] as a generalization of recursive neural networks that can directly deal with a more general class of graphs [30].”
BackgroundQin, L., Li, Z., Che, W., Ni, M., & Liu, T. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i15.17616 · Cited by 72
Exploring Periodicity and Interactivity in Multi-Interest Framework for Sequential Recommendation
Chen, G., Zhang, X., Zhao, Y., Xue, C., & Xiang, J. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/197 · Cited by 82
MultiVision: Designing Analytical Dashboards with Deep Learning Based Recommendation
Wu, A., Wang, Y., Zhou, M., He, X., Zhang, H., Qu, H., & Zhang, D. (2021) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2021.3114826 · Cited by 86
Ariyadasa, S. N., Fernando, S., & Fernando, S. (2022) · IEEE Access · doi:10.1109/access.2022.3196018 · Cited by 82
“In general, graph (G) is a pair of nodes (V) and edges (E) which can denote G(V, E) [60].”
BackgroundFew-shot Molecular Property Prediction via Hierarchically Structured Learning on Relation Graphs
Ju, W., Liu, Z., Qin, Y., Feng, B., Wang, C., Guo, Z., Luo, X., & Zhang, M. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.03.034 · Cited by 86
Wang, H., Zhang, Z., Li, X., Deng, X., & Jiang, W. R. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3322481 · Cited by 72
“Meanwhile, graph neural network (GNN) [38], [39] has offered new insights and approaches to tackle spatial dependencies.”
BackgroundCLOOME: contrastive learning unlocks bioimaging databases for queries with chemical structures
Sanchez-Fernandez, A., Rumetshofer, E., Hochreiter, S., & Klambauer, G. (2023) · Nature Communications · doi:10.1038/s41467-023-42328-w · Cited by 104
Liu, Z., Huang, L., Gao, Z., Luo, M., Hosseinalipour, S., & Dai, H. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3387707 · Cited by 84
“GNNs are capable of adaptively extracting discriminative features for each node of a graph based on the topological information aggregated from its neighboring nodes [41].”
BackgroundVulnerability Detection via Multiple-Graph-Based Code Representation
Qiu, F., Liu, Z., Hu, X., Xia, X., Chen, G., & Wang, X. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3427815 · Cited by 80
“In recent years, Graph Neural Network (GNN) [33], such as Graph Convolutional Network (GCN) [34], Graph Attention Network (GAT) [35], Gated Graph Sequence Neural Networks (GGNN) [36], has been shown to be effective in modeling graph data, e.g., social networks [12], traffic networks [13].”
Background
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.