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 301–400 of 1,052
A Review on Deep Learning Techniques for 3D Sensed Data Classification
Griffiths, D., & Boehm, J. (2019) · Remote Sensing · doi:10.3390/rs11121499 · Cited by 228
“Further Graph CNNs have been proposed using either spatial filtering [114] or spectral filtering”
MethodGraph U-NetsPreprint
Gao, H., & Ji, S. (2019) · arXiv (Cornell University) · Cited by 231
Graph Neural Networks in TensorFlow and Keras with Spektral [Application Notes]
Grattarola, D., & Alippi, C. (2021) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2020.3039072 · Cited by 205
Graph Edge Convolutional Neural Networks for Skeleton-Based Action Recognition
Zhang, X., Xu, C., Tian, X., & Tao, D. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2935173 · Cited by 205
Combinatorial optimization with physics-inspired graph neural networks
Schuetz, M. J. A., Brubaker, J. K., & Katzgraber, H. G. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00468-6 · Cited by 203
HGAT: Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification
Yang, T., Hu, L., Shi, C., Ji, H., Li, X., & Nie, L. (2021) · ACM Transactions on Information Systems · doi:10.1145/3450352 · Cited by 203
Combinatorial Optimization and Reasoning with Graph Neural Networks
Cappart, Q., Chételat, D., Khalil, E. B., Lodi, A., Morris, C., & Veličković, P. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/595 · Cited by 202
Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
Lei, H., Akhtar, N., & Mian, A. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2983410 · Cited by 202
Context Aware Graph Convolution for Skeleton-Based Action Recognition
Zhang, X., Xu, C., & Tao, D. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01434 · Cited by 200
“2) Spatial perspective - Works in this stream directly design convolution by weighted summation of vertices on spatial domain [19, 26].”
BackgroundTransPolymer: a Transformer-based language model for polymer property predictions
Xu, C., Wang, Y., & Barati Farimani, A. (2023) · npj Computational Materials · doi:10.1038/s41524-023-01016-5 · Cited by 199
“Graph neural networks (GNNs), 12 which have outperformed many other models on several molecules and polymer benchmarks, 13–17 are capable of learning representations from graphs and finding optimal fingerprints based on downstream tasks.”
BackgroundBayesian Graph Convolutional Neural Networks for Semi-Supervised Classification
Zhang, Y., Pal, S., Coates, M., & Ustebay, D. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33015829 · Cited by 199
Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
Jin, W., Yang, K., Barzilay, R., & Jaakkola, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.01070 · Cited by 118
“Previous work on graph encoders includes convolutional (Scarselli et al., 2009; Bruna et al., 2013; Henaff et al., 2015; Duvenaud et al., 2015; Niepert et al., 2016; Defferrard et al., 2016; Kondor et al., 2018) and recurrent architectures (Li et al., 2015; Dai et al., 2016; Lei et al., 2017).”
BackgroundProvably Powerful Graph NetworksPreprint
Maron, H., Ben-Hamu, H., Serviansky, H., & Lipman, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.11136 · Cited by 401
“The pioneering works that applied neural networks to graphs are Gori et al. (2005); Scarselli et al. (2009) that learn node representations using recurrent neural networks, which were also used in Li et al. (2015).”
BackgroundInnovative Materials Science via Machine Learning
Gao, C., Min, X., Fang, M., Tao, T., Zheng, X., Liu, Y., Wu, X., & Huang, Z. (2022) · Advanced Functional Materials · doi:10.1002/adfm.202108044 · Cited by 198
A Survey on Neural Architecture Search
Wistuba, M., Rawat, A., & Pedapati, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.01392 · Cited by 198
“(2019) extend this idea by combining it with a graph neural network (Scarselli et al., 2009) which directly operates on a graph defined by nodes and edges.”
BackgroundGated Graph Recurrent Neural Networks
Ruiz, L., Gama, F., & Ribeiro, A. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.3033962 · Cited by 198
Metro Passenger Flow Prediction via Dynamic Hypergraph Convolution Networks
Wang, J., Zhang, Y., Wei, Y., Hu, Y., Piao, X., & Yin, B. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3072743 · Cited by 198
ReGVD: Revisiting Graph Neural Networks for Vulnerability Detection
Nguyen, V.-A., Nguyen, D. Q., Nguyen, V., Le, T., Tran, Q. H., & Phung, D. (2022) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse-companion55297.2022.9793807 · Cited by 252
Diffusion models in bioinformatics and computational biology
Guo, Z., Liu, J., Wang, Y., Chen, M., Wang, D., Xu, D., & Cheng, J. (2023) · Nature Reviews Bioengineering · doi:10.1038/s44222-023-00114-9 · Cited by 139
Tak, H., Jung, J.-W., Patino, J., Kamble, M., Todisco, M., & Evans, N. (2021) · 2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge · doi:10.21437/asvspoof.2021-1 · Cited by 197
Intelligent financial fraud detection practices in post-pandemic era
Zhu, X., Ao, X., Qin, Z., Chang, Y., Liu, Y., He, Q., & Li, J. (2021) · The Innovation · doi:10.1016/j.xinn.2021.100176 · Cited by 197
“It thus motivates graph-based DL and Graph Neural Networks (GNNs) widely applied in the financial fraud detection areas since the graph is a natural choice for presenting relational data.(122,126,127,142,143) Homogeneous relations.”
Modeling intercellular communication in tissues using spatial graphs of cells
Fischer, D. S., Schaar, A. C., & Theis, F. J. (2023) · Nature Biotechnology · doi:10.1038/s41587-022-01467-z · Cited by 196
Metrics for graph comparison: A practitioner’s guide
Wills, P., & Meyer, F. G. (2020) · PLOS ONE · doi:10.1371/journal.pone.0228728 · Cited by 196
“, [54–57] and references therein).”
Graph Neural Networks in IoT: A Survey
Dong, G., Tang, M., Wang, Z., Gao, J., Guo, S., Cai, L., Gutierrez, R., Campbel, B., Barnes, L. E., & Boukhechba, M. (2023) · ACM Transactions on Sensor Networks · doi:10.1145/3565973 · Cited by 196
“GCN-based GNNs: instead of aggregating node signals from spatial domains in MPNNs/GNs, GCN-based GNNs learn MAI representations from spectral domains.”
BackgroundInfluentialGuest Editorial: Deep Neural Networks for Graphs: Theory, Models, Algorithms, and Applications
Li, M., Micheli, A., Wang, Y. G., Pan, S., Lió, P., Gnecco, G. S., & Sanguineti, M. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3371592 · Cited by 196
How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses
Costa, J. C., Roxo, T., Proença, H. P. M. C., & Inácio, P. R. M. (2024) · IEEE Access · doi:10.1109/access.2024.3395118 · Cited by 253
“Detector Graph (DG) [113] considers graphs to detect the adversarial examples by constructing a Latent Neighborhood Graph (LNG) for each original example and using Graph Neural Networks (GNNs) [114] to exploit the relationship and distinguish between original and adversarial examples.”
MethodFoundations & Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions
Liang, P. P., Zadeh, A., & Morency, L.-P. (2024) · ACM Computing Surveys · doi:10.1145/3656580 · Cited by 195
“Hudson and Man-ning [140] designed a neural state machine to simulate the execution of a question being asked about an image, while using discrete words as intermediate concepts.”
BackgroundDeep learning for post-processing ensemble weather forecasts
Grönquist, P., Yao, C., Ben-Nun, T., Dryden, N., Dueben, P., Li, S., & Hoefler, T. (2021) · Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rsta.2020.0092 · Cited by 195
“ng. Recurrent networks that encompass more time steps, as well as deep learning models that are capable of working on the native unstructured grid of the prediction model (e.g., graph neural networks [48]), can also be investigated in this context. Finally, the presented improvements would need to be studied when appl…”
BackgroundA Survey of Event Extraction From Text
Xiang, W., & Wang, B. (2019) · IEEE Access · doi:10.1109/access.2019.2956831 · Cited by 195
“Recently, many neural networks operating on graphs, or called graph neural networks (GNNs) as a general reference, have been recently prompted for a wide range of application domains [175]–[177].”
BackgroundDeep learning analysis on microscopic imaging in materials science
Ge, M., Su, F., Zhao, Z., & Su, D. (2020) · Materials Today Nano · doi:10.1016/j.mtnano.2020.100087 · Cited by 195
A Systematic Survey on Deep Generative Models for Graph Generation
Guo, X., & Zhao, L. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3214832 · Cited by 151
“Purely node and edge attribute transformation have been handled in node classification or link prediction task by typical GNNs [74], [97], thus are not the focus of our survey.”
MethodIs Homophily a Necessity for Graph Neural Networks?Preprint
Ma, Y., Liu, X., Shah, N., & Tang, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.06134 · Cited by 270
“(Scarselli et al., 2008) proposed the first GNN model, to tackle both node and graph level tasks.”
BackgroundMethodDeep Learning Approaches on Image Captioning: A Review
Ghandi, T., Pourreza, H., & Mahyar, H. (2024) · ACM Computing Surveys · doi:10.1145/3617592 · Cited by 194
An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem
Joshi, C. K., Laurent, T., & Bresson, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.01227 · Cited by 193
“In contrast to autoregressive approaches, Nowak et al. [2017] trained a graph neural network [Scarselli et al., 2009] in a supervised manner to directly output a tour as an adjacency matrix, which is converted into a feasible solution using beam search.”
MethodFlexible Neural Representation for Physics Prediction
Mrowca, D., Zhuang, C., Wang, E., Haber, N., Fei-Fei, L., Tenenbaum, J. B., & Yamins, D. L. K. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.08047 · Cited by 156
“Our work draws inspiration from and extends that of Chang et al. [11] and Battaglia et al. [4], which in turn use ideas from graph-based neural networks [39, 44, 9, 30, 22, 14, 13, 24, 8, 40].”
ResultResearch commentary on recommendations with side information: A survey and research directions
Sun, Z., Guo, Q., Yang, J., Fang, H., Guo, G., Zhang, J., & Burke, R. (2019) · Electronic Commerce Research and Applications · doi:10.1016/j.elerap.2019.100879 · Cited by 192
“Third, as the NFs can be considered as a graph, other graph related DLMs can also be adopted, including graph convolutional networks (GCN) (Duvenaud et al. 2015; Niepert et al. 2016) and graph neural network (GNN) (Scarselli et al. 2008).”
AI Applications through the Whole Life Cycle of Material Discovery
Li, J., Lim, K., Yang, H., Ren, Z., Raghavan, S., Chen, P.-Y., Buonassisi, T., & Wang, X. (2020) · Matter · doi:10.1016/j.matt.2020.06.011 · Cited by 192
“Sequential data through time can be regarded as an acyclic directed graph, 87 and molecules are often best represented as an undirected graph with atoms as the nodes and bonds between atoms as the edges.”
Machine-enabled inverse design of inorganic solid materials: promises and challenges
Noh, J., Gu, G. H., Kim, S., & Jung, Y. (2020) · Chemical Science · doi:10.1039/d0sc00594k · Cited by 190
Xiao, Q., Liu, K., Hong, Y., & Tang, H. (2024) · ACS In Focus · doi:10.1021/acsinfocus.7e8012 · Cited by 190
Li, C. (2019) · Reinforcement Learning for Cyber-Physical Systems · doi:10.1201/9781351006620-6 · Cited by 188
Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective
Lamb, L. C., Garcez, A. D., Gori, M., Prates, M., Avelar, P., & Vardi, M. Y. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/679 · Cited by 241
Self-citationLayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis
Shen, Z., Zhang, R., Dell, M., Lee, B. C. G., Carlson, J., & Li, W. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86549-8_9 · Cited by 268
Heterogeneous Graph Neural Network via Attribute Completion
Jin, D., Huo, C., Liang, C., & Yang, L. (2021) · Proceedings of the Web Conference 2021 · doi:10.1145/3442381.3449914 · Cited by 187
Complex network classification with convolutional neural network
Xin, R., Zhang, J., & Shao, Y. (2020) · Tsinghua Science and Technology · doi:10.26599/tst.2019.9010055 · Cited by 187
“Some models, such as GNNs[12], GGSNN[13], and GCN[14], use deep learning techniques to deal with”
MethodTopological Map Extraction From Overhead Images
Li, Z., Wegner, J. D., & Lucchi, A. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00180 · Cited by 185
“A recent extension of this work [1] increases the output resolution by adding a graph neural network (GNN) [43, 25].”
BackgroundIdentity-aware Graph Neural Networks
You, J., Gomes-Selman, J. M., Ying, R., & Leskovec, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i12.17283 · Cited by 332
Yu, X., Tang, B., & Zhang, K. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3048799 · Cited by 184
“Inspired by Scarselli et al. [16], Mikolov et al. [17] and Perozzi et al. [18] proposed the deep walk theory in 2014, which allowed graphical representation learning in the era of deep learning.”
BackgroundMethodContrastive Learning of Structured World Models
Kipf, T., van der Pol, E., & Welling, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.12247 · Cited by 66
“Environment transitions are modeled using a graph neural network (Scarselli et al., 2009; Li et al., 2015; Kipf & Welling, 2016; Gilmer et al., 2017; Battaglia et al., 2018) that operates on latent abstract representations.”
MethodHyperbolic Deep Neural Networks: A Survey
Peng, W., Varanka, T., Mostafa, A., Shi, H., & Zhao, G. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3136921 · Cited by 183
“Originally, GNN is proposed by [94], [95] as an approach for learning graph node representations via neural networks.”
BackgroundFine-grained Fact Verification with Kernel Graph Attention Network
Liu, Z., Xiong, C., Sun, M., & Liu, Z. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.655 · Cited by 183
“It conducts reasoning and aggregation over claim evidence pairs with 1https://competitions.codalab.org/ competitions/18814 a graph model (Veličković et al., 2017; Scarselli et al., 2008; Kipf and Welling, 2017).”
BackgroundGraph networks for molecular design
Mercado, R., Rastemo, T., Lindelöf, E., Klambauer, G., Engkvist, O., Chen, H., & Jannik Bjerrum, E. (2021) · Machine Learning: Science and Technology · doi:10.1088/2632-2153/abcf91 · Cited by 183
“Introduced by Scarselli et al in 2008 [25, 28], many GNN variants have since been reported in the literature, the majority applied to molecules only in the past couple of years [16, 20, 27, 29].”
BackgroundSuperGraph: Spatial-Temporal Graph-Based Feature Extraction for Rotating Machinery Diagnosis
Yang, C., Zhou, K., & Liu, J. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3075871 · Cited by 183
“proposed to build a neural network for data held in the graph domain based on graph theory [19].”
BackgroundA survey on interpretable reinforcement learning
Glanois, C., Weng, P., Zimmer, M., Li, D., Yang, T., Hao, J., & Liu, W. (2024) · Machine Learning · doi:10.1007/s10994-024-06543-w · Cited by 245
“…(Battaglia et al., 2018) stand out as an effective way to compute interactions between entities and can support combinatorial generalization to some extent (Battaglia et al., 2018; Cranmer et al., 2020; Gilmer et al., 2017; Li et al., 2017c; Sanchez-Gonzalez et al., 2018; Scarselli et al., 2009).”
Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction
Wang, Y., Min, Y., Chen, X., & Wu, J. (2021) · Proceedings of the Web Conference 2021 · doi:10.1145/3442381.3449786 · Cited by 182
“onvolutional neural network to non-Euclidean spaces, providing a more natural and effective way for modeling graph-structured data[9]. In recent years, numerous powerful GNN architectures are reported[1, 6, 11, 16, 18, 24, 37, 43, 49, 50, 53]. With the development of various GNNs and variants, modern GNNs have achieve…”
BackgroundGraph Neural Networks with Generated Parameters for Relation Extraction
Zhu, H., Lin, Y., Liu, Z., Fu, J., Chua, T.-S., & Sun, M. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1128 · Cited by 182
“GNNs were first proposed in (Scarselli et al., 2009) and are trained via the Almeida-Pineda algorithm (Almeida, 1987).”
MethodAggregation-Based Graph Convolutional Hashing for Unsupervised Cross-Modal Retrieval
Zhang, P.-F., Li, Y., Huang, Z., & Xu, X.-S. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3053766 · Cited by 182
Specifying Object Attributes and Relations in Interactive Scene Generation
Ashual, O., & Wolf, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00466 · Cited by 182
“2, is captured by the equations: ) where G is the graph convolutional network [9, 20] that generates the per-object layout embedding, M and B are the networks that generate the object’s mask and its bounding box, respectively, T is the fixed (unlearned) function that maps the various object…”
BackgroundNicholls, J., Kuppa, A., & Le-Khac, N.-A. (2021) · IEEE Access · doi:10.1109/access.2021.3134076 · Cited by 181
“RGNNs were first introduced by [18] by extending the recursive neural network, and Markov chain approach.”
MethodMissing data imputation with adversarially-trained graph convolutional networks
Spinelli, I., Scardapane, S., & Uncini, A. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.06.005 · Cited by 181
“Some of the earliest work on extending NNs to the graph domain were presented in Gori et al. (2005); Scarselli et al. (2009), and later reformulated in Li et al. (2015) in a more recent context.”
BackgroundLow-Rank Matrix Completion: A Contemporary Survey
Nguyen, L. T., Kim, J., & Shim, B. (2019) · IEEE Access · doi:10.1109/access.2019.2928130 · Cited by 181
Fake news detection: A survey of graph neural network methods
Phan, H. T., Nguyên, N. T., & Hwang, D. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110235 · Cited by 213
“…neural networks (GNNs ) which are an extension of recurrent neural networks (RNNs), were first introduced by Scarselli et al. [168] by considering an information diffusion mechanism, where states of nodes are updated and information is exchanged until a stable equilibrium is obtained [167,168].”
BackgroundGraph Neural Networks Exponentially Lose Expressive Power for Node Classification
Oono, K., & Suzuki, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.10947 · Cited by 180
“Our approach, which considers the asymptotic behaviors graph CNNs as the layer size goes to infinity, is similar to [44], one of the earliest works about graph CNNs.”
Graph neural networks in particle physics
Shlomi, J., Battaglia, P., & Vlimant, J.-R. (2021) · Machine Learning: Science and Technology · doi:10.1088/2632-2153/abbf9a · Cited by 180
“The first GNNs [32,33] were developed and applied for network analysis, especially on internet data, and were trained not with the back-propagation algorithm, but with fixed point iteration via the Almeida-Pineda algorithm [34, 35].”
BackgroundMethodNetwork Digital Twin: Context, Enabling Technologies, and Opportunities
Almasan, P., Ferriol-Galmes, M., Paillisse, J., Suarez-Varela, J., Perino, D., Lopez, D., Perales, A. A. P., Harvey, P., Ciavaglia, L., Wong, L., et al. (2022) · IEEE Communications Magazine · doi:10.1109/mcom.001.2200012 · Cited by 180
“Graph neural networks (GNN) are a DL-based architecture recently proposed by the ML community to model relational information [9].”
BackgroundDecoding the tumor microenvironment with spatial technologies
Walsh, L. A., & Quail, D. F. (2023) · Nature Immunology · doi:10.1038/s41590-023-01678-9 · Cited by 180
“The predominant methods for spatial clustering derive from two foundational strategies: hidden Markov random field (HMRF) 121 and graph neural networks (GNNs) 122 .”
MethodZamanakos, G., Tsochatzidis, L., Amanatiadis, A., & Pratikakis, I. (2021) · Computers & Graphics · doi:10.1016/j.cag.2021.07.003 · Cited by 180
Learning to Solve NP-Complete Problems: A Graph Neural Network for Decision TSP
Prates, M., Avelar, P., Lemos, H., Lamb, L. C., & Vardi, M. Y. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33014731 · Cited by 109
Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review
Jin, H., Zhang, E., & Espinosa, H. D. (2023) · Applied Mechanics Reviews · doi:10.1115/1.4062966 · Cited by 200
“Graph neural networks [83] are a type of ML method that is usually employed on graph-structured data, which can be considered as a collection of nodes and edges.”
MethodUnleashing the Power of Artificial Intelligence in Materials Design
Badini, S., Regondi, S., & Pugliese, R. (2023) · Materials · doi:10.3390/ma16175927 · Cited by 179
“GNNs are a type of ANN designed to process and analyze graph-structured data [41].”
BackgroundGraph neural networks in node classification: survey and evaluation
Xiao, S., Wang, S., Dai, Y., & Guo, W. (2022) · Machine Vision and Applications · doi:10.1007/s00138-021-01251-0 · Cited by 179
“As a result, graph neural networks (GNNs) have been developed rapidly and achieved a series of break-throughs [31–33].”
BackgroundGraph-FCN for Image Semantic Segmentation
Lu, Y., Chen, Y., Zhao, D., & Chen, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-22796-8_11 · Cited by 202
Message Passing Neural Networks
Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O., & Dahl, G. E. (2020) · Lecture notes in physics · doi:10.1007/978-3-030-40245-7_10 · Cited by 253
A Critical Review of Communications in Multi-robot Systems
Gielis, J., Shankar, A., & Prorok, A. (2022) · Current Robotics Reports · doi:10.1007/s43154-022-00090-9 · Cited by 239
“This was concurrently developed by a line of work that builds on Graph Neural Networks (GNNs), which are permutation equivariant by design [127–129].”
MethodDeep Learning for Time Series Forecasting: Advances and Open Problems
Casolaro, A., Capone, V., Iannuzzo, G., & Camastra, F. (2023) · Information · doi:10.3390/info14110598 · Cited by 178
“A recent promising research direction in multivariate time series forecasting is the application of Graph Neural Networks (GNNs) [124,125].”
BackgroundRetinal Vessel Segmentation Using Deep Learning: A Review
Chen, C., Chuah, J. H., Ali, R., & Wang, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3102176 · Cited by 178
“To consider the graphical structure of vessel shape, Shin, et al. [137] proposed a vessel graphic network that combined a graph neural network (GNN) [41] with a CNN to jointly utilize both local appearance and global vessel structure.”
BackgroundMethodRemote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information
Yuan, Z., Zhang, W., Tian, C., Rong, X., Zhang, Z., Wang, H., Fu, K., & Sun, X. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3163706 · Cited by 178
“To process the data in graph domain, Scarselli et al. [32] first proposed GNN model and the supervised learning algo-rithm were derived to estimate the parameters of the model.”
Molecular generative Graph Neural Networks for Drug Discovery
Bongini, P., Bianchini, M., & Scarselli, F. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.04.039 · Cited by 177
“On the other hand, Graph Neural Networks (GNNs) [14], with their capability of processing graph–structured data without loss of connectivity information, allow to build very powerful generative models.”
BackgroundMethodInfluentialSelf-citationZhao, X., Jia, M., & Liu, Z. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3034189 · Cited by 177
“Under the guidance of a small amount of category labeling information, SSL assists the tasks such as feature extraction and classification or clustering by mining a large number of unlabeled sample structure information [20], [22].”
BackgroundInfluentialApplications of transformer-based language models in bioinformatics: a survey
Zhang, S., Fan, R., Liu, Y., Chen, S., Liu, Q., & Zeng, W. (2023) · Bioinformatics Advances · doi:10.1093/bioadv/vbad001 · Cited by 176
Learning a SAT Solver from Single-Bit Supervision
Selsam, D., Lamm, M., Bünz, B., Liang, P., de Moura, L., & Dill, D. L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.03685 · Cited by 176
“We believe that their network’s success is an instance of the phenomenon we study in this paper, namely that MPNNs can synthesize local search algorithms for constraint satisfaction problems.”
BackgroundMethodInfluentialMachine learning for numerical weather and climate modelling: a review
de Burgh-Day, C. O., & Leeuwenburg, T. (2023) · Geoscientific Model Development · doi:10.5194/gmd-16-6433-2023 · Cited by 176
word2vec, node2vec, graph2vec, X2vec: Towards a Theory of Vector Embeddings of Structured Data
Grohe, M. (2020) · Proceedings of the 39th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems · doi:10.1145/3375395.3387641 · Cited by 176
“al networks (GNNs) are a deep learning framework for graphs that avoids both of these diculties, albeit at the price of limited expressiveness (see Section 3). Early forms of GNNs were introduced in [90, 36]; the version we present here is based on [58, 49, 88]. Intuitively, a GNN model can be thought of as a message…”
Scale-Aware Graph Neural Network for Few-Shot Semantic Segmentation
Xie, G.-S., Liu, J., Xiong, H., & Shao, L. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00543 · Cited by 176
“GNNs [11, 12, 26] are useful tools for modeling the structural relationships among various kinds of input data, e.g., they have been used for video understanding [35,37], biology structure prediction [11], graph-structured data classification [32], object detection [45], and zero-shot learning [38,…”
BackgroundMethodSpAGNN: Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data
Casas, S., Gulino, C., Liao, R., & Urtasun, R. (2020) · 2020 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra40945.2020.9196697 · Cited by 176
“Towards this goal, we propose an efficient probabilistic model that leverages recent advances in graph neural networks (GNNs) [18] to capture the interactions between vehicles.”
BackgroundMethodSpatio-Temporal Analysis and Prediction of Cellular Traffic in Metropolis
Wang, X., Zhou, Z., Xiao, F., Xing, K., Yang, Z., Liu, Y., & Peng, C. (2019) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2018.2870135 · Cited by 176
“To efficiently learn the spatio-temporal dependency in cell tower traffic, we adopt a Graph Neural Network (GNN) [40] model.”
MethodAn efficient Lorentz equivariant graph neural network for jet tagging
Gong, S., Meng, Q., Zhang, J., Qu, H., Li, C., Qian, S., Du, W., Ma, Z.-M., & Liu, T. (2022) · Journal of High Energy Physics · doi:10.1007/jhep07(2022)030 · Cited by 201
“Graph neural networks are natural to learn representations for graph structured data [13].”
BackgroundDifferentiation of Blackbox Combinatorial SolversPreprint
Vlastelica, M., Paulus, A., Musil, V., Martius, G., & Rolínek, M. (2019) · arXiv (Cornell University) · doi:10.17617/3.yjcq5s · Cited by 298
Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link PredictionPreprint
Zhu, Z., Zhang, Z., Xhonneux, L.-P., & Tang, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.06935 · Cited by 596
“Graph neural networks (GNNs) [47, 33, 60, 65] are a family of representation learning models that encode topological structures of graphs.”
BackgroundSIGN: Scalable Inception Graph Neural Networks
Frasca, F., Rossi, E., Eynard, D., Chamberlain, B., Bronstein, M. M., & Monti, F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.11198 · Cited by 175
“Graph neural networks (GNNs) seek to generalize classical convolutional architectures (CNNs) to graph-structured data, with a wide variety of convolution-like operations available in the literature [52, 14, 2, 45, 54, 42, 32, 59, 57, 22].”
BackgroundLearning Combinatorial Embedding Networks for Deep Graph Matching
Wang, R., Yan, J., & Yang, X. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00315 · Cited by 175
“Each GNN layer has a feature dimension of 2048.”
BackgroundInfluentialRhee, S., Seo, S., & Kim, S. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/490 · Cited by 175
Neural networks for power flow: Graph neural solver
Donon, B., Clément, R., Donnot, B., Marot, A., Guyon, I., & Schoenauer, M. (2020) · Electric Power Systems Research · doi:10.1016/j.epsr.2020.106547 · Cited by 234
“in [26] and further developed in [21], [13], and their theoretical properties have been investigated in [17], [30].”
BackgroundI Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences
Oliynyk, D., Mayer, R. L., & Rauber, A. (2023) · ACM Computing Surveys · doi:10.1145/3595292 · Cited by 258
Semi-Supervised Classification of Graph Convolutional Networks with Laplacian Rank Constraints
Zhang, H., Lu, G., Zhan, M., & Zhang, B. (2022) · Neural Processing Letters · doi:10.1007/s11063-020-10404-7 · Cited by 174
A Survey on Embedding Dynamic Graphs
Barros, C. D. T., Mendonça, M. R. F., Vieira, A. B., & Ziviani, A. (2023) · ACM Computing Surveys · doi:10.1145/3483595 · Cited by 174
Towards Robust Pattern Recognition: A Review
Zhang, X.-Y., Liu, C., & Suen, C. Y. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.2989782 · Cited by 202
“contextual learning, and recently graph neural networks [244], [141], [289] have gained increasing popularity in various domains by modeling the dependencies between nodes in a graph via efficient and effective message passing among them.”
BackgroundOn failure modes in molecule generation and optimization
Renz, P., Van Rompaey, D., Wegner, J. K., Hochreiter, S., & Klambauer, G. (2019) · Drug Discovery Today: Technologies · doi:10.1016/j.ddtec.2020.09.003 · Cited by 154
“Another range of models directly generate molecular graphs, using graph neural networks [18].”
BackgroundGraph Filters for Signal Processing and Machine Learning on Graphs
Isufi, E., Gama, F., Shuman, D. I., & Segarra, S. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3349788 · Cited by 217
“VII) and an activation function that is (typically) pointwise and nonlinear [4], [23], [181].”
Molecular Geometry Prediction using a Deep Generative Graph Neural Network
Mansimov, E., Mahmood, O., Kang, S., & Cho, K. (2019) · Scientific Reports · doi:10.1038/s41598-019-56773-5 · Cited by 130
“ight matrices and b prior m and b prior s are the bias terms of the transformations. These are used to form the prior distribution: logP(ZjG)= N å i=1 3 å j=1 (m i;j z i;j) 2 2s2 i;j 2log q 2ps i;j ; (12) where m i;j and s i 2 ;j are the j-th components of the mean and variance vectors respectively. In other words, we…”
MethodGraphite: Iterative Generative Modeling of GraphsPreprint
Grover, A., Zweig, A., & Ermon, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.10459 · Cited by 323
“To effectively model the relational structure of large graphs for deep learning, prior works have proposed to use graph neural networks [11, 37, 4].”
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.