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 101–200 of 1,052
Abdelrahman, G., Wang, Q., & Nunes, B. (2023) · ACM Computing Surveys · doi:10.1145/3569576 · Cited by 468
“Such a graph is clustered into node groups and for each group a shared embedding is constructed using GNNs to get the final recommendations.”
MethodOpen Domain Question Answering Using Early Fusion of Knowledge Bases and Text
Sun, H., Dhingra, B., Zaheer, M., Mazaitis, K., Salakhutdinov, R., & Cohen, W. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1455 · Cited by 716
“The GRAFT-Net model itself is motivated from the large body of work on graph representation learning (Scarselli et al., 2009; Li et al., 2016; Kipf and Welling, 2016; Atwood and Towsley, 2016; Schlichtkrull et al., 2017).”
BackgroundEEG emotion recognition using fusion model of graph convolutional neural networks and LSTM
Yin, Y., Zheng, X., Hu, B., Zhang, Y., & Cui, X. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106954 · Cited by 466
Bhatti, U. A., Tang, H., Wu, G., Marjan, S., & Hussain, A. (2023) · International Journal of Intelligent Systems · doi:10.1155/2023/8342104 · Cited by 462
Discriminative Embeddings of Latent Variable Models for Structured Data
Dai, H., Dai, B., & Song, L. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.05629 · Cited by 454
“Scarselli et al. (2009) proposed a neural network which generates features by solving a heuristic nonlinear system iteratively, and is learned using Almeida-Pineda algorithm.”
Corso, G., Stark, H., Jegelka, S., Jaakkola, T., & Barzilay, R. (2024) · Nature Reviews Methods Primers · doi:10.1038/s43586-024-00294-7 · Cited by 454
Dynamic graph convolutional networks
Manessi, F., Rozza, A., & Manzo, M. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2019.107000 · Cited by 446
“In the last couple of years, a number of research works have revisited the problem of generalizing neural networks to work on arbitrarily structured graphs [1,3,4,12,15,20], some of them achieving promising results in domains that have been previously dominated by other techniques.”
BackgroundCross-Sentence N-ary Relation Extraction with Graph LSTMs
Peng, N., Poon, H., Quirk, C., Toutanova, K., & Yih, W.-T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00049 · Cited by 443
“Generalizing such a strategy to graphs with cycles typically requires unrolling recurrence for a number of steps (Scarselli et al., 2009; Li et al., 2016; Liang et al., 2016).”
BackgroundKnowledge-Embedded Routing Network for Scene Graph Generation
Chen, T., Yu, W., Chen, R., & Lin, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00632 · Cited by 432
“Then, our model adopts a graph neural network [27, 17] to propagate”
MethodGraph Neural Networks with Convolutional ARMA Filters
Bianchi, F. M., Grattarola, D., Livi, L., & Alippi, C. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3054830 · Cited by 426
A Review of Graph Neural Networks and Their Applications in Power Systems
Liao, W., Bak-Jensen, B., Radhakrishna Pillai, J., Wang, Y., & Wang, Y. (2022) · Journal of Modern Power Systems and Clean Energy · doi:10.35833/mpce.2021.000058 · Cited by 426
GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
Huang, Q., Yamada, M., Tian, Y., Singh, D., & Chang, Y. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3187455 · Cited by 424
“GNNs [10] recursively incorporate the node feature information and structure information of a graph from the neighborhood into a neural network”
BackgroundEfficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++
Acuna, D., Ling, H., Kar, A., & Fidler, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00096 · Cited by 414
Learning to Simulate Complex Physics with Graph Networks
Sánchez‐González, Á., Godwin, J., Pfaff, T., Ying, R., Leskovec, J., & Battaglia, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09405 · Cited by 413
“Graph networks (GN) (Battaglia et al., 2018)—a type of graph neural network (Scarselli et al., 2008)—have recently proven effective at learning forward dynamics in various settings that involve interactions between many entities.”
BackgroundSkeleton-based action recognition via spatial and temporal transformer networks
Plizzari, C., Cannici, M., & Matteucci, M. (2021) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2021.103219 · Cited by 409
FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
Chen, J., Ma, T., & Xiao, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.10247 · Cited by 406
“…a view, yet, generalizes to many graph models whose formulations are based on first-order neighborhoods, examples of which include MoNet that applies to (meshed) manifolds (Monti et al., 2017), as well as many message-passing neural networks (see e.g., Scarselli et al. (2009); Gilmer et al. (2017)).”
BackgroundSkeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning
Si, C., Jing, Y., Wang, W., Wang, L., & Tan, T. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01246-5_7 · Cited by 400
Graph Neural Networks and Their Current Applications in Bioinformatics
Zhang, X.-M., Liang, L., Liu, L., & Tang, M.-J. (2021) · Frontiers in Genetics · doi:10.3389/fgene.2021.690049 · Cited by 397
“For example, graph embedding algorithms are used to perform the mapping of graph structure data to simpler representations (Scarselli et al., 2008).”
MethodGeom-GCN: Geometric Graph Convolutional Networks
Pei, H., Wei, B., Chang, K. C., Yu, L., & Yang, B. X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.05287 · Cited by 396
“Message-passing neural networks (MPNNs), such as GNN (Scarselli et al., 2008), ChebNet (Deffer-rard et al., 2016), GG-NN (Li et al., 2016), GCN (Kipf & Welling, 2017), are powerful for learning on graphs with various applications ranging from brain networks to online social network (Gilmer et al.,…”
BackgroundHow to build the virtual cell with artificial intelligence: Priorities and opportunities
Bunne, C., Roohani, Y., Rosen, Y., Gupta, A., Zhang, X., Roed, M., Alexandrov, T., AlQuraishi, M., Brennan, P., Burkhardt, D. B., et al. (2024) · Cell · doi:10.1016/j.cell.2024.11.015 · Cited by 393
“150 Graphs, sets of nodes connected by edges, are useful representations for many kinds of biological data.”
Fake news detection on social media using geometric deep learning
Monti, F., Frasca, F., Eynard, D., Mannion, D., & Bronstein, M. M. (2019) · arXiv · doi:10.48550/arxiv.1902.06673 · Cited by 392
“Early approaches to learning on graphs [34] predate the recent deep learning renaissance and are formulated as fixed points of learnable diffusion operators.”
BackgroundGraph networks as learnable physics engines for inference and control
Sanchez-Gonzalez, A., Heess, N., Springenberg, J. T., Merel, J., Riedmiller, M., Hadsell, R., & Battaglia, P. (2018) · arXiv · doi:10.48550/arxiv.1806.01242 · Cited by 387
“Our approach uses “graph networks” (GNs), a class of neural networks that can learn functions on graphs (Scarselli et al., 2009b; Li et al., 2015; Battaglia et al., 2016; Gilmer et al., 2017).”
MethodHeterogeneous Graph Neural Networks for Malicious Account Detection
Liu, Z., Chen, C., Yang, X., Zhou, J., Li, X., & Song, L. (2018) · Proceedings of the 27th ACM International Conference on Information and Knowledge Management · doi:10.1145/3269206.3272010 · Cited by 387
“ped. 2.1 Graph Neural Networks The first class is concerned with predicting labels over a graph, its edges, or its nodes. Graph Neural Networks were introduced in Gori et al.[11] and Scarselli et al. [19] as a generalization of recursive neural networks that can directly deal with a more general class of graphs, e.g.…”
BackgroundInfluentialA Fair Comparison of Graph Neural Networks for Graph ClassificationPreprint
Errica, F., Podda, M., Bacciu, D., & Micheli, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.09893 · Cited by 446
“Graph Neural Networks (GNNs) (Micheli, 2009; Scarselli et al., 2008) have recently become the standard tool for machine learning on graphs.”
BackgroundMethodLearning Deep Generative Models of Graphs
Li, Y., Vinyals, O., Dyer, C., Pascanu, R., & Battaglia, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.03324 · Cited by 385
“Originally developed in (Scarselli et al., 2009), a range of variants of such graph structured neural net models have been developed and applied to various graph problems more recently (Henaff et al., 2015; Li et al., 2016; Kipf & Welling, 2016; Battaglia et al., 2016; Gilmer et al., 2017).”
How to Train Your Energy-Based Models
Song, Y., & Kingma, D. P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.03288 · Cited by 79
“For example, If the data are graphs (such as molecules) then one could use graph neural networks (Scarselli et al., 2008); if the data are spherical images one can in principle use spherical CNNs (Cohen et al.”
MethodGraph-to-Sequence Learning using Gated Graph Neural Networks
Beck, D., Haffari, G., & Cohn, T. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1026 · Cited by 380
Solving Mixed Integer Programs Using Neural NetworksPreprint
Nair, V. B., Bartunov, S., Gimeno, F., von Glehn, I., Lichocki, P., Lobov, I., O’Donoghue, B., Sonnerat, N., Tjandraatmadja, C., Wang, P., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.13349 · Cited by 464
“The key deep learning architecture we use is a form of graph neural network (Scarselli et al. (2009), see survey by Battaglia et al. (2018)), specifically a graph convolutional network (GCN) (Kipf and Welling 2016).”
MethodAttention is all you need: utilizing attention in AI-enabled drug discovery
Zhang, Y., Liu, C., Liu, M., Liu, T., Lin, H., Huang, C.-B., & Ning, L. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad467 · Cited by 377
“Graph Neural Networks (GNNs) have shown significant efficacy for these non-Euclidean data by learning the representation of nodes, edges or the entire graph through information propagation and aggregation [50– 52].”
BackgroundScaling Graph Neural Networks with Approximate PageRank
Bojchevski, A., Gasteiger, J., Perozzi, B., Kapoor, A., Blais, M., Rózemberczki, B., Lukasik, M., & Günnemann, S. (2020) · Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3394486.3403296 · Cited by 371
RouteNet: Leveraging Graph Neural Networks for Network Modeling and Optimization in SDN
Rusek, K., Suarez-Varela, J., Almasan, P., Barlet-Ros, P., & Cabellos-Aparicio, A. (2020) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3000405 · Cited by 366
“In this paper we present RouteNet, a novel network model based on Graph Neural Networks (GNN) [10].”
MethodFew-Shot Learning with Graph Neural Networks
García, V., & Bruna, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.04043 · Cited by 364
“Following several recent works that cast posterior inference using message passing with neural networks defined over graphs Scarselli et al. (2009); Duvenaud et al. (2015); Gilmer et al. (2017), we associate T with a fully-connected graph G T = ( V, E ) where nodes v a ∈ V correspond to the images…”
Gated Graph Sequence Neural Networks
Li, Y., Tarlow, D., Brockschmidt, M., & Zemel, R. S. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.05493 · Cited by 362
“Several variants are discussed in Scarselli et al. (2009) including positional graph forms, node-specific updates, and alternative representations of neighborhoods.”
BackgroundMethodInfluentialSignal propagation in complex networks
Ji, P., Ye, J., Mu, Y., Lin, W., Tian, Y., Hens, C., Perc, M., Tang, Y., Sun, J., & Kurths, J. (2023) · Physics Reports · doi:10.1016/j.physrep.2023.03.005 · Cited by 360
Deep Parametric Continuous Convolutional Neural Networks
Wang, S., Suo, S., Ma, W.-C., Pokrovsky, A., & Urtasun, R. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00274 · Cited by 359
“Graph Neural Networks: Graph neural networks (GNNs) [25] are generalizations of neural networks to graph structured data.”
BackgroundWu, Y., Sicard, B., & Gadsden, S. A. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124678 · Cited by 357
Artificial intelligence for digital and computational pathology
Song, A. H., Jaume, G., Williamson, D. F. K., Lu, M. Y., Vaidya, A., Miller, T. R., & Mahmood, F. (2023) · Nature Reviews Bioengineering · doi:10.1038/s44222-023-00096-8 · Cited by 356
“Deep learning in pathology has also been used for developing AI-based assistive tools that can extract actionable objects and representations”
MethodParameterized Explainer for Graph Neural Network
Luo, D., Cheng, W., Xu, D., Yu, W., Zong, B., Chen, H., & Zhang, X. (2020) · arXiv · doi:10.48550/arxiv.2011.04573 · Cited by 355
“The study of GNNs was initiated in [17], and then extended in [41].”
BackgroundRetrieving and Reading: A Comprehensive Survey on Open-domain Question Answering
Zhu, F., Lei, W., Wang, C., Zheng, J., Poria, S., & Chua, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.00774 · Cited by 143
“Then, graph CNN based methods [101], [121], [122] are used to infer the final answer over the sub-graph.”
MethodPart-Aware Prototype Network for Few-Shot Semantic Segmentation
Liu, Y., Zhang, X., Zhang, S., & He, X. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58545-7_9 · Cited by 353
Holzinger, A., Malle, B., Saranti, A., & Pfeifer, B. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.01.008 · Cited by 352
“Graph Neural Networks (GNN) have been known for quite a while and are a well-established method to learn from graph structures [47, 48].”
MethodVideo Summarization Using Deep Neural Networks: A Survey
Apostolidis, E., Adamantidou, E., Metsai, A. I., Mezaris, V., & Patras, I. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3117472 · Cited by 350
Position-aware Graph Neural NetworksPreprint
You, J., Ying, R., & Leskovec, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.04817 · Cited by 615
“Node embedding methods can be categorized into Graph Neural Networks (GNNs) approaches (Scarselli et al., 2009),”
MethodUnderstanding over-squashing and bottlenecks on graphs via curvature
Topping, J., Giovanni, F. D., Chamberlain, B. P., Dong, X., & Bronstein, M. M. (2021) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.48550/arxiv.2111.14522 · Cited by 495
“…particular graph neural networks (GNNs) (Sperduti, 1994; Goller & Kuchler, 1996; Sperduti & Starita, 1997; Frasconi et al., 1998; Gori et al., 2005; Scarselli et al., 2008; Bruna et al., 2014; Defferrard et al., 2016; Kipf & Welling, 2017; Gilmer et al., 2017) have become very popular in the…”
BackgroundDeep Learning for Medical Image-Based Cancer Diagnosis
Jiang, X., Hu, Z., Wang, S., & Zhang, Y. (2023) · Cancers · doi:10.3390/cancers15143608 · Cited by 345
Tama, B. A., Vania, M., Lee, S., & Lim, S. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10293-3 · Cited by 345
“(11) 2.2.5 Graph neural network (GNN) Scarselli et al. (2009) first proposed GNNs, which aim to use graph theory to develop a neural network that could model graph data.”
BackgroundInfluentialUnveiling the predictive power of static structure in glassy systems
Bapst, V., Keck, T., Grabska-Barwińska, A., Donner, C., Cubuk, E. D., Schoenholz, S. S., Obika, A., Nelson, A. W. R., Back, T., Hassabis, D., et al. (2020) · Nature Physics · doi:10.1038/s41567-020-0842-8 · Cited by 341
Graph Neural Networks in Network Neuroscience
Bessadok, A., Mahjoub, M. A., & Rekik, I. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3209686 · Cited by 341
“GNN was designed for node classification where each node in the graph is associatedwith a label [45].”
MethodA Comprehensive Survey on Deep Graph Representation Learning
Ju, W., Fang, Z., Gu, Y., Liu, Z., Long, Q., Qiao, Z., Qin, Y., Shen, J., Sun, F., Xiao, Z., et al. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106207 · Cited by 341
Graph Information Aggregation Cross-Domain Few-Shot Learning for Hyperspectral Image Classification
Zhang, Y., Li, W., Zhang, M., Wang, S., Tao, R., & Du, Q. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3185795 · Cited by 340
“GNN was first designed for tasks on processing graph-structured data [36], which mainly represents the characteristics of central nodes by neighborhood aggregation and transforming neighboring nodes recursively.”
MethodRethinking the Item Order in Session-based Recommendation with Graph Neural Networks
Qiu, R., Li, J., Huang, Z., & YIn, H. (2019) · Proceedings of the 28th ACM International Conference on Information and Knowledge Management · doi:10.1145/3357384.3358010 · Cited by 339
CCNet: Criss-Cross Attention for Semantic Segmentation
Huang, Z., Wang, X., Wei, Y., Huang, L., Shi, H., Liu, W., & Huang, T. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.11721 · Cited by 338
Invariant and Equivariant Graph NetworksPreprint
Maron, H., Ben-Hamu, H., Shamir, N., & Lipman, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.09902 · Cited by 376
“Gori et al. (2005); Scarselli et al. (2009) introduced Graph Neural Networks (GNN): GNNs hold a state (a real valued vector) for each node in the graph, and propagate these states according to the graph structure and learned parametric functions.”
BackgroundGraph-Based Semi-Supervised Learning: A Comprehensive Review
Song, Z., Yang, X., Xu, Z., & King, I. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3155478 · Cited by 334
“Thebasic GNN message passing [19] is defined as follows : where W ( k ) self , W ( k ) neigh are trainable parameters and σ is the activation function.”
BackgroundFoundations and Modeling of Dynamic Networks Using Dynamic Graph Neural Networks: A Survey
Skarding, J., Gabrys, B., & Musial, K. (2021) · IEEE Access · doi:10.1109/access.2021.3082932 · Cited by 331
Gao, J., Zhang, T., & Xu, C. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00478 · Cited by 328
“On one hand, some methods adopt feed-forward neural networks to every node in a spatial manner [55].”
MethodPullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
Sun, H., Bedrax-Weiss, T., & Cohen, W. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1242 · Cited by 327
“, 2018) supports multihop reasoning on both KBs and text by introducing a question subgraph built with facts and text, and uses a learned graph representation (Kipf and Welling, 2016; Li et al., 2016; Schlichtkrull et al., 2017; Scarselli et al., 2009) to perform the reasoning required to select the answer.”
BackgroundMethodA Comprehensive Survey of Scene Graphs: Generation and Application
Chang, X., Ren, P., Xu, P., Li, Z., Chen, X., & Hauptmann, A. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3137605 · Cited by 324
“GCN (Graph Convolutional Network) [85], [86], [87], [88] is just such a method.”
MethodPerson Re-identification with Deep Similarity-Guided Graph Neural Network
Shen, Y., Li, H., Yi, S., Chen, D., & Wang, X. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01267-0_30 · Cited by 324
Deep multi-view learning methods: A review
Yan, X., Hu, S., Mao, Y., Ye, Y., & Yu, H. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.03.090 · Cited by 322
“Recently, Graph neural networks (GNN) [73] reconciles the expressive power of graphs in modeling interactions with deep models in terms of learning representation and has gained increasing attention due to its capability of modeling720 graph structured data.”
BackgroundInfluentialSpectral Clustering with Graph Neural Networks for Graph PoolingPreprint
Bianchi, F. M., Grattarola, D., & Alippi, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.00481 · Cited by 357
“Many approaches have been proposed to process a graph with a neural network, including recurrent architectures (Scarselli et al., 2009; Li et al., 2015) or convolutional operations inspired by filters used in graph signal processing (Defferrard et al.”
BackgroundDeep learning for geological hazards analysis: Data, models, applications, and opportunities
Ma, Z., & Mei, G. (2021) · Earth-Science Reviews · doi:10.1016/j.earscirev.2021.103858 · Cited by 321
Graph Convolutional Networks with EigenPooling
Ma, Y., Wang, S., Aggarwal, C. C., & Tang, J. (2019) · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3292500.3330982 · Cited by 320
“nnnnnnn on this topic is usually under the name of “Graph Neural Networks” [34], which typically involves transforming, propagating and aggregating node features across the graph.”
BackgroundHamilton, W. L. (2020) · Synthesis lectures on artificial intelligence and machine learning · doi:10.2200/s01045ed1v01y202009aim046 · Cited by 320
“We begin here with the most basic GNN framework, which is a simplification of the original GNN model proposed by Scarselli et al. [2009]. The basic GNN message passing is defined as”
MethodWang, H., Wang, K., Yang, J., Shen, L., Sun, N., Lee, H.-S., & Han, S. (2020) · 2020 57th ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac18072.2020.9218757 · Cited by 320
“[23] used GNN to replace an EM simulator for distributed circuits.”
BackgroundInfluentialAI in drug discovery and its clinical relevance
Qureshi, R., Irfan, M., Gondal, T. M., Khan, S., Wu, J., Hadi, M. U., Heymach, J., Le, X., Yan, H., & Alam, T. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e17575 · Cited by 319
“GNNs are designed to work with graph data, which represents relationships between entities, such as chemical compounds and proteins [106].”
Explainability in deep reinforcement learning
Heuillet, A., Couthouis, F., & Díaz-Rodríguez, N. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106685 · Cited by 319
Deep Time Series Models: A Comprehensive Survey and Benchmark
Wang, Y., Wu, H., Dong, J., Liu, Y. H., Wang, C., Long, M., & Wang, J. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3690845 · Cited by 393
“To address this, Graph neural networks (GNNs) [134], [135] have been widely adopted in time series analysis.”
Rai, R., & Sahu, C. K. (2020) · IEEE Access · doi:10.1109/access.2020.2987324 · Cited by 315
“Other techniques like spectral CNNs [264], [265], graph CNNs [266], [267], geodesic CNNs [268], manifold learning should be explored for CPS applications.”
BackgroundThe More You Know: Using Knowledge Graphs for Image Classification
Marino, K., Salakhutdinov, R., & Gupta, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.10 · Cited by 315
Text Level Graph Neural Network for Text Classification
Huang, L., Ma, D., Li, S., Zhang, X., & Wang, H. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1345 · Cited by 314
“So GNN are proposed (Scarselli et al., 2009) to apply deep learning techniques to data in graph domain.”
MethodA federated graph neural network framework for privacy-preserving personalization
Wu, C., Wu, F., Lyu, L., Qi, T., Huang, Y., & Xie, X. (2022) · Nature Communications · doi:10.1038/s41467-022-30714-9 · Cited by 311
Multi-label Zero-Shot Learning with Structured Knowledge Graphs
Lee, C.-W., Fang, W., Yeh, C.-K., & Wang, Y.-C. F. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00170 · Cited by 305
Transformers in Time-Series Analysis: A Tutorial
Ahmed, S., Nielsen, I. E., Tripathi, A., Siddiqui, S., Ramachandran, R. P., & Rasool, G. (2023) · Circuits, Systems, and Signal Processing · doi:10.1007/s00034-023-02454-8 · Cited by 305
“The Traffic Transformer [12] has been built based on two existing networks, the first being a Graph Neural Network [74, 102] followed by the Transformer as shown in Fig.”
MethodInfluentialA gentle introduction to deep learning for graphs
Bacciu, D., Errica, F., Micheli, A., & Podda, M. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.06.006 · Cited by 305
Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
Wang, W., Lu, X., Shen, J., Crandall, D., & Shao, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00933 · Cited by 303
“In [53], recurrent neural networks were used to model the state of each node, and the underlying correlation between nodes are learned via parameterized message passing over neighbors.”
BackgroundMethodDyRep: Learning Representations over Dynamic Graphs
Trivedi, R., Farajtabar, M., Biswal, P., & Hongyuan Zha, B. (2019) · International Conference on Learning Representations · Cited by 944
ConvPoint: Continuous convolutions for point cloud processing
Boulch, A. (2020) · Computers & Graphics · doi:10.1016/j.cag.2020.02.005 · Cited by 302
“Neural networks on graphs were pioneered in [42].”
BackgroundAWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing
Geng, T., Li, A., Shi, R., Wu, C., Wang, T., Li, Y., Haghi, P., Tumeo, A., Che, S., Reinhardt, S., et al. (2020) · 2020 53rd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro50266.2020.00079 · Cited by 301
“In the past decade, work has continued on optimizing GNN algorithms exploring new neural network approaches [8], [19], [20], [22]–[25].”
BackgroundSeo, H., Badiei Khuzani, M., Vasudevan, V., Huang, C., Ren, H., Xiao, R., Jia, X., & Xing, L. (2020) · Medical Physics · doi:10.1002/mp.13649 · Cited by 300
“Scarselli et al. 128 first introduced GNNs and directly applied existing neural networks to graph domain.”
BackgroundChen, Z., Xu, J., Peng, T., & Yang, C. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3059002 · Cited by 300
“The theoretical basis of GCN was first given by Scarselli et al. [21].”
BackgroundExplainability Techniques for Graph Convolutional NetworksPreprint
Baldassarre, F., & Azizpour, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.13686 · Cited by 411
“Several variants of GN have been proposed starting from the early work of (Scarselli et al., 2009).”
BackgroundSyntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks
Huang, B., & Carley, K. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1549 · Cited by 299
“, 2017) is a variant of graph neural network (Scarselli et al., 2009) and is a key element in our method.”
MethodReview and prospect of data-driven techniques for load forecasting in integrated energy systems
Zhu, J., Dong, H., Zheng, W., Li, S., Huang, Y., & Xi, L. (2022) · Applied Energy · doi:10.1016/j.apenergy.2022.119269 · Cited by 298
Relational Graph Attention Networks
Busbridge, D., Sherburn, D., Cavallo, P., & Hammerla, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.05811 · Cited by 120
“This architecture is the same as in Schlichtkrull et al. (2018) except with RGCNs replaced with RGATs.”
BackgroundResultCTNet: Conversational Transformer Network for Emotion Recognition
Lian, Z., Liu, B., & Tao, J. (2021) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2021.3049898 · Cited by 296
“Recently, graph-based models have received growing attentions [39].”
BackgroundEnd-to-End Constrained Optimization Learning: A Survey
Kotary, J., Fioretto, F., Hentenryck, P. V., & Wilder, B. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/610 · Cited by 373
Knowledge Transfer for Out-of-Knowledge-Base Entities : A Graph Neural Network Approach
Hamaguchi, T., Oiwa, H., Shimbo, M., & Matsumoto, Y. (2017) · Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/250 · Cited by 291
Deep reinforcement learning meets graph neural networks: Exploring a routing optimization use case
Almasan, P., Suárez-Varela, J., Rusek, K., Barlet-Ros, P., & Cabellos-Aparicio, A. (2022) · Computer Communications · doi:10.1016/j.comcom.2022.09.029 · Cited by 290
“Recently, Graph Neural Networks (GNN) [23] have been proposed to model and operate over graphs with the aim of achieving relational reasoning and combinatorial generalization.”
BackgroundDetecting Code Clones with Graph Neural Network and Flow-Augmented Abstract Syntax Tree
Wang, W., Li, G., Ma, B., Xia, X., & Jin, Z. (2020) · 2020 IEEE 27th International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner48275.2020.9054857 · Cited by 287
“The concept of GNN was first proposed in [10].”
BackgroundComputing Graph Neural Networks: A Survey from Algorithms to Accelerators
Abadal, S., Jain, A., Guirado, R., López-Alonso, J., & Alarcón, E. (2022) · ACM Computing Surveys · doi:10.1145/3477141 · Cited by 285
MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
Batatia, I., Kovács, D. P., Simm, G. N. C., Ortner, C., & Cśanyi, G. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.07697 · Cited by 285
“MPNNs [22, 9] are a type of graph neural network (GNN, [40, 4, 27, 51]) that parametrises a mapping from a labeled graph to a target space, either a graph or a vector space.”
BackgroundGenerating Classification Weights With GNN Denoising Autoencoders for Few-Shot Learning
Gidaris, S., & Komodakis, N. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00011 · Cited by 284
“This is a family of deep learning networks designed to process an unordered set of entities (in our case a set of classes) associated with a graph G such that they take into account their inter-entity relationships (in our case inter-class relationships) when making predictions about them [11, 34, 20, 6, 37] (for a re…”
BackgroundGraph-based deep learning for communication networks: A survey
Jiang, W. (2022) · Computer Communications · doi:10.1016/j.comcom.2021.12.015 · Cited by 284
“Routing [85] Graph-Query Neural Network GNN [89]”
BackgroundMethodInfluentialNazir, S., Dickson, D. M., & Akram, M. U. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106668 · Cited by 283
“The model and the learning al-gorithm, output functions, comparison with Random Walks and Recursive Neural Networks, and complexity were derived mathematically [99].”
BackgroundMethodInfluentialHow to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
Ye, J., Zhao, J., Ye, K., & Xu, C. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3043250 · Cited by 281
TUDataset: A collection of benchmark datasets for learning with graphs
Morris, C., Kriege, N. M., Bause, F., Kersting, K., Mutzel, P., & Neumann, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08663 · Cited by 281
“Recently, graph neural networks (Gilmer et al., 2017; Scarselli et al., 2009) emerged as an alternative to graph kernels.”
BackgroundA Comprehensive Review on Fake News Detection With Deep Learning
Mridha, M. F., Keya, A. J., Hamid, M. A., Monowar, M. M., & Rahman, M. S. (2021) · IEEE Access · doi:10.1109/access.2021.3129329 · Cited by 281
“The network extends recursive neural networks by processing a broader class of graphs, including directed, undirected graphs, and cyclic, and it can handle node-focused applications except any pre-processing steps [138].”
BackgroundHow Neural Networks Extrapolate: From Feedforward to Graph Neural NetworksPreprint
Xu, K., Li, J., Zhang, M., Du, S., Kawarabayashi, K., & Jegelka, S. (2020) · International Conference on Learning Representations · doi:10.48550/arxiv.2009.11848 · Cited by 399
“However, recent works show Graph Neural Networks (GNNs) (Scarselli et al., 2009), a class of structured networks with MLP building blocks, can generalize to graphs much larger than training graphs in challenging algorithmic tasks, such as predicting the time evolution of physical systems (Battaglia…”
BackgroundGraph Matching Networks for Learning the Similarity of Graph Structured Objects
Li, Y., Gu, C., Dullien, T., Vinyals, O., & Kohli, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.12787 · Cited by 278
“ESI , 10 RDI , RBP Graph Neural Networks and Graph Representation Learning The history of graph neural networks (GNNs) goes back to at least the early work by Gori et al. (2005) and Scarselli et al. (2009), who proposed to use a propagation process to learn node representations.”
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.