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 401–500 of 1,052
Rethinking Table Recognition using Graph Neural Networks
Qasim, S. R., Mahmood, H., & Faisal Shafait, B. (2019) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2019.00031 · Cited by 171
“[21] where they formulated a comprehensive graph model based on contraction maps.”
MethodRCD: Relation Map Driven Cognitive Diagnosis for Intelligent Education Systems
Gao, W., Liu, Q., Huang, Z., Yin, Y., Bi, H., Wang, M.-C., Ma, J., Wang, S., & Su, Y. (2021) · Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3404835.3462932 · Cited by 170
“As the state of the art technique, graph neural network (GNN) [14, 17, 37] has shown huge success for modeling graph structures.”
Qasim, S. R., Kieseler, J., Iiyama, Y., & Pierini, M. (2019) · The European Physical Journal C · doi:10.1140/epjc/s10052-019-7113-9 · Cited by 204
Automated Seismic Source Characterization Using Deep Graph Neural Networks
van den Ende, M., & Ampuero, J. (2020) · Geophysical Research Letters · doi:10.1029/2020gl088690 · Cited by 176
“Fortunately, much progress has been made in the field of graph neural networks (GNNs; Gori et al., 2005; Scarselli et al., 2009; Zhou et al., 2019), providing a robust framework for analyzing non-Euclidean data using existing deep learning tools.”
BackgroundDegas, A., Islam, M. R., Hurter, C., Barua, S., Rahman, H., Poudel, M., Ruscio, D., Ahmed, M. U., Begum, S., Rahman, M. A., et al. (2022) · Applied Sciences · doi:10.3390/app12031295 · Cited by 168
“The latest work on a graph neural network [67] could possibly become important in modelling in the future, such as modelling actual ATCOs [68].”
BackgroundLearning Discrete Structures for Graph Neural Networks
Franceschi, L., Niepert, M., Pontil, M., & He, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.11960 · Cited by 167
“Graph neural networks (GNNs) (Scarselli et al., 2009) are one such”
BackgroundMachine Learning in Polymer Research
Ge, W., De Silva, R., Fan, Y., Sisson, S. A., & Stenzel, M. H. (2025) · Advanced Materials · doi:10.1002/adma.202413695 · Cited by 167
Graph Neural Networks for Modelling Traffic Participant Interaction
Diehl, F., Brunner, T., Le, M. T., & Knoll, A. (2019) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2019.8814066 · Cited by 202
“Only fairly recently [6], [7] have GNNs, i.”
BackgroundA survey on graph-based deep learning for computational histopathology
Ahmedt-Aristizabal, D., Armin, M. A., Denman, S., Fookes, C., & Petersson, L. (2022) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2021.102027 · Cited by 147
“Based on the original graph neural networks in [52], we introduce the most representative GNN variants that have been proposed for computational pathology.”
MethodDanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer
Li, B., Zhao, Y., Shi, Z., & Sheng, L. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20014 · Cited by 250
“The experimental result shows that GNN has better performances compared to the base-line (“KPM to Linear”), which proves that introducing spatial correlations benefits the representation of the learning model.”
MethodInfluentialCross-Modal Retrieval: A Systematic Review of Methods and Future Directions
Wang, T., Li, F., Zhu, L., Li, J., Zhang, Z., & Shen, H. T. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3525147 · Cited by 247
“Video Audio”
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
Ponomareva, N., Hazimeh, H., Kurakin, A., Xu, Z., Denison, C., McMahan, H. B., Vassilvitskii, S., Chien, S., & Thakurta, A. G. (2023) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.14649 · Cited by 166
“An additional complication of GNN networks is that during inference time, the same (training) graph structure is reused for predictions, and it needs to be DP-protected as well (on top of DP-Training of GNN models) (Daigavane et al., 2021).”
BackgroundInfluentialMultimodal learning with graphs
Ektefaie, Y., Dasoulas, G., Noori, A., Farhat, M., & Zitnik, M. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00624-6 · Cited by 166
“The predominant use of graph neural networks [8] is to learn representations of various graph components—such as nodes, edges, subgraphs, and entire graphs—based on neural message passing strategies.”
BackgroundGraph Prototypical Networks for Few-shot Learning on Attributed Networks
Ding, K., Wang, J., Li, J., Shu, K., Liu, C., & Liu, H. (2020) · Proceedings of the 29th ACM International Conference on Information & Knowledge Management · doi:10.1145/3340531.3411922 · Cited by 166
“s Driven by the momentous success of deep learning, recently, a mass of efforts have been devoted to developing deep neural networks for graph-structured data [3, 4]. As one of the pioneer works, GNN [29] was introduced to learn node representations by propagating neighbors’ information via recurrent neural architectu…”
BackgroundFang, X., Huang, J., Wang, F., Zeng, L., Liang, H., & Wang, H. (2020) · Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3394486.3403320 · Cited by 166
“Recently, there is increasing interest in graph neural networks (GNNs) [5, 13, 20].”
BackgroundAdaptive Graph Representation Learning for Video Person Re-Identification
Wu, Y., Bourahla, O. E. F., Li, X., Wu, F., Tian, Q., & Zhou, X. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3001693 · Cited by 166
“As shown in Figure 4, we employ Graph Neural Network (GNN) [35] to aggregate the information from neighbors for each node.”
MethodThe Surprising Power of Graph Neural Networks with Random Node Initialization
Abboud, R., Ceylan, İ. İ., Grohe, M., & Lukasiewicz, T. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/291 · Cited by 272
Constructing Neural Network Based Models for Simulating Dynamical Systems
Legaard, C. M., Schranz, T., Schweiger, G., Drgoňa, J., Falay, B., Gomes, C. Â. G., Iosifidis, A., Abkar, M., & Larsen, P. G. (2023) · ACM Computing Surveys · doi:10.1145/3567591 · Cited by 194
Universal Invariant and Equivariant Graph Neural Networks
Keriven, N., & Gabriel Peyré, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.04943 · Cited by 126
“Early definitions of these “message passing” architectures rely on fixed point iterations (Scarselli et al., 2009), while more recent constructions make use of non-linear functions of the adjacency matrix, for instance using spectral decompositions (Bruna et al.”
BackgroundGeometric and Physical Quantities Improve E(3) Equivariant Message PassingPreprint
Brandstetter, J., Hesselink, R., van der Pol, E., Bekkers, E. J., & Welling, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.02905 · Cited by 307
“Graph neural networks (GNNs) (Scarselli et al., 2009; Kipf & Welling, 2017; Defferrard et al., 2016; Battaglia et al., 2018) are designed to learn from graph-structured data and are by construction permutation equivariant with respect to the input.”
BackgroundA Comprehensive Survey of Graph Neural Networks for Knowledge Graphs
Ye, Z., Kumar, Y. J., Sing, G. O., Song, F., & Wang, J. (2022) · IEEE Access · doi:10.1109/access.2022.3191784 · Cited by 164
Learning Combinatorial Optimization on Graphs: A Survey With Applications to Networking
Vesselinova, N., Steinert, R., Perez-Ramirez, D. F., & Boman, M. (2020) · IEEE Access · doi:10.1109/access.2020.3004964 · Cited by 164
“A node’s hidden state is recurrently updated in [37] by exchanging information (node embeddings) with neighboring nodes until a stable equilibrium is reached:”
BackgroundInfluentialGE-GAN: A novel deep learning framework for road traffic state estimation
Xu, D., Wei, C., Peng, P., Xuan, Q., & Guo, H. (2020) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2020.102635 · Cited by 164
GraphMix: Improved Training of GNNs for Semi-Supervised Learning
Verma, V., Qu, M., Kawaguchi, K., Lamb, A., Bengio, Y., Kannala, J., & Tang, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i11.17203 · Cited by 220
“Early work includes (Gori, Monfardini, and Scarselli 2005; Scarselli et al. 2009) which propose a neural network that can directly process most types of graphs e.g., acyclic, cyclic, directed, and undirected graphs.”
BackgroundMixup for Node and Graph Classification
Wang, Y., Wang, W., Liang, Y., Cai, Y., & Hooi, B. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3449796 · Cited by 256
“More recently, many efforts have been made to design graph neural networks (GNNs) for graph classification [42], [32], [37], [19], [63], [69], [60].”
BackgroundDocument-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation
Tan, Q., He, R., Bing, L., & Ng, H. T. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.132 · Cited by 220
Lei, L., Yang, Q., Yang, L., Shen, T., Wang, R., & Fu, C. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10775-6 · Cited by 191
Boosting coverage-based fault localization via graph-based representation learning
Lou, Y., Zhu, Q., Dong, J., Li, X., Sun, Z., Hao, D., Zhang, L., & Zhang, L. (2021) · Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3468264.3468580 · Cited by 163
“Therefore, in Grace, we design a GGNN model to learn key features in the unified coverage graph and to rank suspicious code nodes in the graph.”
BackgroundInfluentialDETERRENT: Knowledge Guided Graph Attention Network for Detecting Healthcare Misinformation
Cui, L., Seo, H., Tabar, M., Ma, F., Wang, S., & Lee, D. (2020) · Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3394486.3403092 · Cited by 163
“The Information Propagation Net is replaced by a GNN model.”
InfluentialWang, Y., Xu, T., Niu, X., Tan, C., Chen, E., & Xiong, H. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2020.3033782 · Cited by 163
“Our proposed method is also related to recent advances of Graph Neural Network (GNN) [49]–[52].”
MethodRepresentation Learning in Multi-view Clustering: A Literature Review
Chen, M.-S., Lin, J.-Q., Li, X.-L., Liu, B.-Y., Wang, C.-D., Huang, D., & Lai, J.-H. (2022) · Data Science and Engineering · doi:10.1007/s41019-022-00190-8 · Cited by 163
“Apart from the autoencoder as well as GNN-based deep representation learning for MVC methods, some other attempts have also been made by researchers.”
MethodGCNAX: A Flexible and Energy-efficient Accelerator for Graph Convolutional Neural Networks
Li, J., Louri, A., Karanth, A., & Bunescu, R. (2021) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca51647.2021.00070 · Cited by 200
“GNNs can be categorized into recurrent graph neural networks (RecGNNs) [20], graph convolutional neural networks (GCNs), graph autoencoders (GAEs) [21], and spatial-temporal graph neural networks (STGNNs) [22].”
BackgroundZhang, Y., & Lee, A. A. (2019) · Chemical Science · doi:10.1039/c9sc00616h · Cited by 156
Joint-Bone Fusion Graph Convolutional Network for Semi-Supervised Skeleton Action Recognition
Tu, Z., Zhang, J., Li, H., Chen, Y., & Yuan, J. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3168137 · Cited by 171
“firstly proposed a graph neural network (GNN) to handle the graph structure data [50] based on the conventional neural network.”
BackgroundRouteNet-Fermi: Network Modeling With Graph Neural Networks
Ferriol-Galmés, M., Paillissé, J., Suárez‐Varela, J., Rusek, K., Xiao, S., Shi, X., Cheng, X., Barlet‐Ros, P., & Cabellos‐Aparicio, A. (2023) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2023.3269983 · Cited by 196
“Since the introduction of Graph Neural Networks [37], they have already been applied to different fields such as chemistry [14] or logistics [15].”
BackgroundMethodGraph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph KernelsPreprint
Du, S. S., Hou, K., Póczos, B., Salakhutdinov, R., Wang, R., & Xu, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.13192 · Cited by 339
“Many GNNs, with different aggregation and graph readout functions, have been proposed under the neighborhood aggregation framework Xu et al. [2019], Scarselli et al. [2009], Li et al. [2016], Kearnes et al. [2016], Ying et al. [2018], Velickovic et al. [2018], Hamilton et al. [2017], Xu et al.…”
MethodWhat Can Neural Networks Reason About?
Xu, K., Li, J., Zhang, M., Du, S. S., Kawarabayashi, K., & Jegelka, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.13211 · Cited by 90
“Originally proposed for learning on graphs [45], GNNs have become a widely used model for reasoning too [8].”
BackgroundInfluentialAdversarial examples for models of code
Yefet, N., Alon, U., & Yahav, E. (2020) · Proceedings of the ACM on Programming Languages · doi:10.1145/3428230 · Cited by 161
“its inputs, and it represents variable names using a vocabulary of learned embeddings. GatedGraphNeuralNetworks(GGNNs)were introduced by Li et al. [29] as an extension to Graph Neural Networks (GNNs) [45]. The main idea is to represent the problem as a graph, and to aggregate the incoming messages to each vertex with…”
BackgroundPersonalized Graph Neural Networks With Attention Mechanism for Session-Aware Recommendation
Zhang, M., Wu, S., Gao, M., Jiang, X., Xu, K., & Wang, L. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.3031329 · Cited by 176
“Previously, in the form of recurrent neural networks, Graph Neural Networks (GNNs) [36], [37] are proposed to operate on directed graphs.”
BackgroundProcess topology convolutional network model for chemical process fault diagnosis
Wu, D., & Zhao, J. (2021) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2021.03.052 · Cited by 165
Operational Research: methods and applications
Petropoulos, F., Laporte, G., Aktaş, E., Alumur, S. A., Archetti, C., Ayhan, H., Battarra, M., Bennell, J. A., Bourjolly, J.-M., Boylan, J. E., et al. (2023) · Journal of the Operational Research Society · doi:10.1080/01605682.2023.2253852 · Cited by 190
Spherical Message Passing for 3D Graph NetworksPreprint
Liu, Y., Wang, L., Liu, M., Zhang, X., Oztekin, B., & Ji, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.05013 · Cited by 181
“Hence, following message passing neural networks (MPNNs) (Scarselli et al., 2008; Gilmer et al., 2017; Vignac et al., 2020), we further propose a novel message passing scheme, known as the spherical message passing (SMP), for realizing the 3DGN framework.”
BackgroundInfluentialChen, C., Wu, Y., Dai, Q., Zhou, H.-Y., Xu, M., Yang, S., Han, X., & Yu, Y. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3445463 · Cited by 160
“Scarselli et al. [14] extended such neural networks to process more types of graphs, such as cyclic and undirected graphs.”
BackgroundDai, M., Demirel, M. F., Liang, Y., & Hu, J.-M. (2021) · npj Computational Materials · doi:10.1038/s41524-021-00574-w · Cited by 160
Graph Neural Networks: Taxonomy, Advances, and Trends
Zhou, Y., Zheng, H., Huang, X., Hao, S., Li, D., & Zhao, J. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3495161 · Cited by 160
“Original spatial GCNNs [52, 53, 55, 194] constitutes a transition function, which must be a contraction map in order to ensure the uniqueness of states, and an update function.”
BackgroundDigital twin enhanced BIM to shape full life cycle digital transformation for bridge engineering
Honghong, S., Gang, Y., Haijiang, L., Tian, Z., & Annan, J. (2023) · Automation in Construction · doi:10.1016/j.autcon.2022.104736 · Cited by 160
Learning to Detect Human-Object Interactions With Knowledge
Xu, B., Wong, Y., Li, J., Zhao, Q., & Kankanhalli, M. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00212 · Cited by 196
“One group of approaches applies feed-forward neural networks to every node of the graph recurrently, for example Graph Neural Network (GNN) [37] and an improved version Gated Graph Neural Network (GGNN) [24].”
BackgroundWang, M., Zhang, Q., Lam, S., Cai, J., & Yang, R. (2020) · Frontiers in Oncology · doi:10.3389/fonc.2020.580919 · Cited by 149
“…been made to develop a wide range of innovative structures of deep neural networks in recent years, such as graph neural networks (GNN), graph convolutional networks (GCN), graph reinforcement learning (GRL), graph auto-encoders (GAE), and graph regression neural networks (GRNN) (59, 61).”
BackgroundTrajectory Prediction for Autonomous Driving Using Spatial-Temporal Graph Attention Transformer
Zhang, K., Feng, X., Wu, L., & He, Z. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3164450 · Cited by 169
“Then, GNNs [36] or Graph Convolutional Networks (GCNs) [37] were employed to capture social interactions among traffic agents.”
MethodBayoudh, K. (2024) · Information Fusion · doi:10.1016/j.inffus.2023.102217 · Cited by 159
Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification
Yan, Y., Qin, J., Chen, J., Liu, L., Zhu, F., Tai, Y., & Shao, L. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00297 · Cited by 159
“Recently, neural networks have been extensively studied for graph learning, leading to the widespread usage of Graph Neural Networks (GNNs) [41, 10, 12, 29, 53].”
BackgroundMasked Relation Learning for DeepFake Detection
Yang, Z., Liang, J., Xu, Y., Zhang, X.-Y., & He, R. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3249566 · Cited by 143
“Similarly, masked graph modeling [40], [41], [42], [43] guides graph neural networks (GNNs) [44] to reconstruct the masked vertices and edges of the graph.”
BackgroundDistance Encoding: Design Provably More Powerful Neural Networks for Graph Representation LearningPreprint
Li, P., Wang, Y., Wang, H., & Leskovec, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.00142 · Cited by 428
“Graph neural networks (GNNs), inheriting the power of neural networks [18], have recently become almost the default choice to learn structural representations in graphs [19].”
BackgroundLanczosNet: Multi-Scale Deep Graph Convolutional Networks
Liao, R., Zhao, Z., Urtasun, R., & Zemel, R. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.01484 · Cited by 158
“For supervised and semi-supervised tasks such as graph or node classification and regression, learning based models can be roughly categorized into two classes, formulated either in terms of graph convolutions [2] or recurrent neural networks [3].”
BackgroundMethodAn evidential classifier based on Dempster-Shafer theory and deep learning
Zheng, T., Xu, P., & Denœux, T. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.03.066 · Cited by 182
“In recent years, with the explosive development of deep learning [29], several models have been developed for precise classification, such as convolutional neural networks (CNNs) [25, 31, 65], recurrent neural networks [33, 39, 40], graph neural networks [53, 54], and deep autoencoders [63, 64].”
BackgroundDGRec: Graph Neural Network for Recommendation with Diversified Embedding Generation
Yang, L., Wang, S., Tao, Y., Sun, J., Liu, X., Yu, P. S., & Wang, T. (2023) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3539597.3570472 · Cited by 216
“Graph neural network [32, 36] is a family of powerful learningmethods for graph-structured data [13, 19, 34].”
BackgroundShen, W., Peng, Z., Wang, X., Wang, H., Cen, J., Jiang, D., Xie, L., Yang, X., & Tian, Q. C. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3246102 · Cited by 195
“[47] proposed group-wise semantic mining (GWSM) to capture cross-image relation among a group of images rather than a pair of images via a graph neural network (GNN) [105].”
BackgroundA GNN-Based Supervised Learning Framework for Resource Allocation in Wireless IoT Networks
Chen, T., Zhang, X., You, M., Zheng, G., & Lambotharan, S. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3091551 · Cited by 175
“The GNN was first proposed to extend the existing neural network mechanisms for processing the data represented in graph domains [26].”
MethodData‐Driven Machine Learning for Understanding Surface Structures of Heterogeneous Catalysts
Li, H., Jiao, Y., Davey, K. R., & Qiao, S. (2023) · Angewandte Chemie International Edition · doi:10.1002/anie.202216383 · Cited by 167
Attention-based graph neural networks: a survey
Sun, C., Li, C., Lin, X., Zheng, T., Meng, F., Rui, X., & Wang, Z. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10577-2 · Cited by 184
“Based on the previous work on GNNs (Scarselli et al. 2008), GGNN introduces GRU with a soft attention mechanism.”
BackgroundMethodLearning visual relationship and context-aware attention for image captioning
Wang, J., Wang, W., Wang, L., Wang, Z., Feng, D. D., & Tan, T. N. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.107075 · Cited by 166
Evidence Integration for Multi-Hop Reading Comprehension With Graph Neural Networks
Song, L., Wang, Z., Yu, M., Zhang, Y., Florian, R., & Gildea, D. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2982894 · Cited by 159
“Since our generated graphs are complex and can have cycles, making it difficult to directly apply a DAG network (e.g. the structure of Coref-GRU), we adopt graph neural networks [11], which can encode arbitrary graphs.”
MethodDifferentiable Hierarchical Graph Grouping for Multi-person Pose Estimation
Jin, S., Liu, W., Xie, E., Wang, W., Qian, C., Ouyang, W., & Luo, P. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58571-6_42 · Cited by 180
Action Assessment by Joint Relation Graphs
Pan, J., Gao, J., & Zheng, W. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00643 · Cited by 193
“The Joint Commonality Module preforms graph convolutions on the Spatial Relation Graph and learns the joint motion features within joint neighbourhoods, which is inspired by the Graph Convolution Networks [25].”
MethodBelay, M. A., Blakseth, S. S., Rasheed, A., & Salvo Rossi, P. (2023) · Sensors · doi:10.3390/s23052844 · Cited by 118
“Several time-series anomaly detection models have been proposed us-ing transformer architectures: a reconstruction-based transformer architecture for early anomaly detection is proposed in [76]; a transformer-based anomaly detection model (TranAD) with an adversarial training procedure is proposed…”
MethodYu, Z., Zhang, C., & Deng, C. (2023) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2023.110534 · Cited by 163
Yin, J., Shen, J., Guan, C., Zhou, D., & Yang, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01151 · Cited by 150
“[41] extend it to different types of graphs.”
BackgroundGraph Neural Networks for Prediction of Fuel Ignition Quality
Schweidtmann, A. M., Rittig, J. G., König, A. A., Grohe, M., Mitsos, A., & Dahmen, M. (2020) · Energy & Fuels · doi:10.1021/acs.energyfuels.0c01533 · Cited by 163
Signed Graph Attention Networks
Huang, J., Shen, H., Hou, L., & Cheng, X. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30493-5_53 · Cited by 215
Deep Learning for Retail Product Recognition: Challenges and Techniques
Wei, Y.-C., Tran, S. N., Xu, S., Kang, B. H., & Springer, M. (2020) · Computational Intelligence and Neuroscience · doi:10.1155/2020/8875910 · Cited by 187
Exploiting Cross-session Information for Session-based Recommendation with Graph Neural Networks
Qiu, R., Huang, Z. H., Li, J., & Yin, H. (2020) · ACM Transactions on Information Systems · doi:10.1145/3382764 · Cited by 178
“Initially, GNN is applied to the simple situation on directed graphs [7, 39].”
MethodData Analytics in Industry 4.0: A Survey
Duan, L., & Xu, L. D. (2021) · Information Systems Frontiers · doi:10.1007/s10796-021-10190-0 · Cited by 184
Times series forecasting for urban building energy consumption based on graph convolutional network
Hu, Y., Cheng, X., Wang, S., Chen, J., Zhao, T., & Dai, E. (2021) · Applied Energy · doi:10.1016/j.apenergy.2021.118231 · Cited by 173
Hänsch, W., Raghunathan, A., Roy, K., Chakrabarti, B., Phatak, C., Wang, C., & Guha, S. (2023) · Advanced Materials · doi:10.1002/adma.202204944 · Cited by 167
Wang, X., Girshick, R., Gupta, A., & He, K. (2017) · arXiv · Cited by 11,689
“These methods and ours are also related to a more abstract model called graph neural networks [41].”
MethodLearning Steady-States of Iterative Algorithms over Graphs
Dai, H., Kozareva, Z., Dai, B., Smola, A. J., & Song, L. (2018) · International Conference on Machine Learning · Cited by 151
A survey of generative AI for de novo drug design: new frontiers in molecule and protein generation
Tang, X., Dai, H., Knight, E., Wu, F., Li, Y., Li, T., & Gerstein, M. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae338 · Cited by 201
“While not generative models on their own, graph neural networks (GNNs) [57]”
Dressing as a Whole: Outfit Compatibility Learning Based on Node-wise Graph Neural Networks
Cui, Z., Li, Z., Wu, S., Zhang, X.-Y., & Wang, L. (2019) · International World Wide Web Conference (WWW) · doi:10.1145/3308558.3313444 · Cited by 164
“utilized multi-layer perceptions (MLP) to update the hidden state of nodes [29].”
MethodWang, Z., Luo, N., & Zhou, P. (2020) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2020.03.004 · Cited by 170
STGAT: Spatial-Temporal Graph Attention Networks for Traffic Flow Forecasting
Kong, X., Xing, W., Wei, X., Bao, P., Zhang, J., & Lu, W. B. (2020) · IEEE Access · doi:10.1109/access.2020.3011186 · Cited by 163
“Graph Neural Networks is first introduced in [19] and [20], which can directly deal with a more general class of graphs, e.g., cyclic, directed and undirected graphs [21].”
BackgroundLocally Private Graph Neural Networks
Sajadmanesh, S., & Gatica-Perez, D. (2021) · Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3460120.3484565 · Cited by 128
“1 INTRODUCTION Following the advances of deep neural networks in various machine learning domains, such as computer vision, natural language understanding, and speech processing, in the past few years, extending deep learning models for graph-structured data has attracted growing interest, leading to the advent of Gra…”
BackgroundIncomplete Contrastive Multi-View Clustering with High-Confidence Guiding
Chao, G., Jiang, Y., & Chu, D. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i10.29000 · Cited by 221
Hierarchical Generation of Molecular Graphs using Structural MotifsPreprint
Jin, W., Barzilay, R., & Jaakkola, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.03230 · Cited by 359
Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?Preprint
Luan, S., Hua, C., Lu, Q., Zhu, J., Zhao, M., Zhang, S., Chang, X.-W., & Precup, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.05641 · Cited by 167
“Combining graph signal processing and convolutional neural networks [19], numerous Graph Neural Networks (GNNs) [29, 7, 12, 30, 15, 24] have been proposed which empirically out-25 perform traditional neural networks on graph-based machine learning tasks, e.g., node classification, graph…”
Conversational question answering: a survey
Zaib, M., Zhang, W. E., Sheng, Q. Z., Mahmood, A., & Zhang, Y. (2022) · Knowledge and Information Systems · doi:10.1007/s10115-022-01744-y · Cited by 192
“The Graph Flow architecture alternates this mechanism with co-attention over the question and the GNN output.”
MethodInfluentialA Survey of mmWave Radar-Based Sensing in Autonomous Vehicles, Smart Homes and Industry
Kong, H., Huang, C., Yu, J., & Shen, X. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3409556 · Cited by 182
“Other studies treat data representations of mmWave signals as graphs and utilize graph neural networks (GNNs) [127] to further process data and extract features, yielding mmpoint-GNN [128], spatial temporal-GNN [129], etc., for human activity recognition or gait recognition.”
Differentiable Graph Module (DGM) for Graph Convolutional Networks
Kazi, A., Cosmo, L., Ahmadi, S., Navab, N., & Bronstein, M. M. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3170249 · Cited by 214
“While dating back to at least [20], it is mainly the recent progress that has made GNNs a useful and popular tool.”
BackgroundComprehensive Survey of Recent Drug Discovery Using Deep Learning
Kim, J., Park, S., Min, D., & Kim, W. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms22189983 · Cited by 167
“A graph neural network is a model designed to learn graph-type data in a DL method [78].”
MethodZhu, J., Wang, J., Han, W., & Xu, D. H. (2022) · Nature Communications · doi:10.1038/s41467-022-29331-3 · Cited by 155
A Brief Survey of Machine Learning and Deep Learning Techniques for E-Commerce Research
Zhang, X., Guo, F., Chen, T., Pan, L., Beliakov, G., & Wu, J. (2023) · Journal of Theoretical and Applied Electronic Commerce Research · doi:10.3390/jtaer18040110 · Cited by 121
TodyNet: Temporal dynamic graph neural network for multivariate time series classification
Liu, H., Yang, D., Liu, X., Chen, X., Liang, Z., Wang, H., Cui, Y., & Gu, J. (2024) · Information Sciences · doi:10.1016/j.ins.2024.120914 · Cited by 182
“Since the concept of Graph Neural Networks (GNNs) was introduced [21], there has been an explosive development”
BackgroundRobust Spatial Filtering With Graph Convolutional Neural Networks
Such, F. P., Sah, S., Dominguez, M. A., Pillai, S., Zhang, C., Michael, A., Cahill, N. D., & Ptucha, R. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2017.2726981 · Cited by 146
“Gated Graph Sequential Neural Networks [24] presented a graph Long Short-Term Memory (LSTM) Recurrent Neural Network model applied to program verification and basic logical reasoning tasks, extending a neural network model that learned a graph encoding from data [25].”
MethodA Comprehensive Survey on Geometric Deep Learning
Cao, W., Yan, Z., He, Z., & He, Z. (2020) · IEEE Access · doi:10.1109/access.2020.2975067 · Cited by 180
“The work of [11] published by Scarselli et al . in 2009 brought back the graph neural network model to the public’s horizon, defined a function that can map graph and any node to a dimensional Euclidean space, and proposed an algorithm to estimate the neural network model parameter with supervised…”
BackgroundSampling Methods for Efficient Training of Graph Convolutional Networks: A Survey
Liu, X., Yan, M., Deng, L., Li, G., Ye, X., & Fan, D. (2021) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2021.1004311 · Cited by 175
Hogan, A., Blomqvist, E., Cochez, M., d’Amato, C., de Melo, G., Gutiérrez, C., Kirrane, S., Gayo, J. E. L., Navigli, R., Neumaier, S., et al. (2021) · Synthesis lectures on data, semantics and knowledge · doi:10.2200/s01125ed1v01y202109dsk022 · Cited by 250
Routing Optimization With Deep Reinforcement Learning in Knowledge Defined Networking
He, Q., Wang, Y., Wang, X., Xu, W., Li, F., Yang, K., & Ma, L. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3235446 · Cited by 160
“Theworkin[2],[7],[13],[14],[15], [16],[17]usedGNNtomodelthetopologicalcharacteristics inthenetwork,allowingforthepredictionssuchaslinkdelay.”
Symbolic Graph Reasoning Meets Convolutions
Liang, X., Hu, Z., Zhang, H., Lin, L., & Xing, E. P. (2018) · neural information processing systems · Cited by 175
Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
Mogadala, A., Kalimuthu, M., & Klakow, D. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.11688 · Cited by 47
“Similarly, graph neural networks (Scarselli et al., 2008; Kipf & Welling, 2016; Battaglia et al., 2018) introduced to tackle graph-structured data has already shown its prominence”
BackgroundPhysics-Guided Deep Learning for Dynamical Systems: A Survey
Wang, R., & Yu, R. (2025) · ACM Computing Surveys · doi:10.1145/3766887 · Cited by 169
“Similarly, recurrent neural networks [118; 57], graph neural networks [125; 71], and capsule networks [119; 56] all impose symmetries.”
Understanding Pooling in Graph Neural Networks
Grattarola, D., Zambon, D., Bianchi, F. M., & Alippi, C. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3190922 · Cited by 205
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.