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 201–300 of 1,052
Deep Clustering: A Comprehensive Survey
Ren, Y., Pu, J., Yang, Z., Xu, J., Li, G., Pu, X., Yu, P. S., & He, L. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3403155 · Cited by 276
“GNNs [151], [152] allow end-to-end differentiable losses over data with arbitrary graph structure and have been applied to a wide range of applications.”
Optimizing Network Structure for 3D Human Pose Estimation
Ci, H., Wang, C., Ma, X., & Wang, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00235 · Cited by 276
“The Graph Convolutional Network (GCN) [3, 5, 6, 8, 10, 14, 27, 28, 34] is a promising alternative for 3 D pose estimation because it only aggregates the features of the “se-lected” nodes to compute features for a node of interest.”
BackgroundToward an Automated Auction Framework for Wireless Federated Learning Services Market
Jiao, Y., Wang, P., Niyato, D., Lin, B., & Kim, D. I. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2020.2994639 · Cited by 273
Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
Ahmedt-Aristizabal, D., Armin, M. A., Denman, S., Fookes, C., & Petersson, L. (2021) · Sensors · doi:10.3390/s21144758 · Cited by 272
“Based on the original graph neural networks proposed in [33], we introduce the most representative GNN variants”
BackgroundMethodDeep learning for insider threat detection: Review, challenges and opportunities
Yuan, S., & Wu, X. (2021) · Computers & Security · doi:10.1016/j.cose.2021.102221 · Cited by 271
Graph Neural Networks for Decentralized Multi-Robot Path Planning
Li, Q., Gama, F., Ribeiro, A., & Prorok, A. (2020) · 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341668 · Cited by 271
“Graph Neural Networks (GNNs) promise to overcome this deficiency [22], [10].”
BackgroundETC: Encoding Long and Structured Inputs in Transformers
Ainslie, J., Ontañón, S., Alberti, C., Cvicek, V., Fisher, Z., Pham, P., Ravula, A., Sanghai, S., Wang, Q., & Yang, L. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.19 · Cited by 268
“A standard Transformer resembles a graph neural network (Scarselli et al., 2008) over a fully connected graph g ; see Ye et al. (2019).”
MethodDeep Learning for Time Series Classification and Extrinsic Regression: A Current Survey
Mohammadi Foumani, N., Miller, L., Tan, C. W., Webb, G. I., Forestier, G., & Salehi, M. (2024) · ACM Computing Surveys · doi:10.1145/3649448 · Cited by 268
“Graph neural networks (GNNs) were first proposed by Scarcelli et al. [120] to learn directly from graph representations of data.”
MethodShaygan, M., Meese, C., Li, W., Zhao, X. (., & Nejad, M. (2022) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2022.103921 · Cited by 267
Graph2Plan: learning floorplan generation from layout graphs
Hu, R., Huang, Z., Tang, Y., Van Kaick, O., Zhang, H., & Huang, H. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392391 · Cited by 266
“The layout graph G is first passed to a graph neural network (GNN) [Scarselli et al. 2009] that embeds each room in the layout into a feature space.”
MethodInfluentialMachine Learning-Powered Encrypted Network Traffic Analysis: A Comprehensive Survey
Shen, M., Ye, K., Liu, X., Zhu, L., Kang, J., Yu, S., Li, Q., & Xu, K. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2022.3208196 · Cited by 265
“• Graph Neural Network (GNN) [47] is a deep learning method that processes the data represented in the graph domain [47].”
MethodYao, S., Guan, R., Huang, X., Li, Z., Sha, X., Yue, Y., Lim, E. G., Seo, H., Man, K. L., Zhu, X., et al. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3307157 · Cited by 265
“To dig deeper into the relationship between sparse point clouds, GNN [297] is a promising research direction in which each point is considered as a node, and edges are the relationship between the points.”
BackgroundMachine Learning on Graphs: A Model and Comprehensive Taxonomy
Chami, I., Abu-El-Haija, S., Perozzi, B., Ré, C., & Murphy, K. P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.03675 · Cited by 92
“The graph neural network model The first formulation of deep learning methods for graph-structured data dates back to the graph neural network (GNN) model [44, 100].”
BackgroundMethodInfluentialKim, J., Kim, H., Kim, H., Lee, D., & Yoon, S. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11223-9 · Cited by 263
Orb: A Fast, Scalable Neural Network PotentialPreprint
Neumann, M., Gin, J., Rhodes, B., Bennett, S., Li, Z., Choubisa, H., Hussey, A., & Godwin, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.22570 · Cited by 303
“…distributions across a diverse range of application areas including vision, biology and spatial processing, by focusing on architectures that are embarrassingly parallel and can be run efficiently on modern hardware [46, 7], despite lacking architectural biases which would suit the target domain.”
BackgroundTrustworthy ai: A computational perspective
Liu, H., Wang, Y., Fan, W., Liu, X., Li, Y., Jain, S., Liu, Y., Jain, A., & Tang, J. (2023) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3546872 · Cited by 261
“A better explainability method predicts M ut ag R ed di t- B in ar y O nl in eD is cu ss io n M ut ag R ed di tB in ar y Q ue st io nAn sw er Computation graph Grad Ground TruthAttComputation graph Grad Att Ground TruthGNNExplainer GNNExplainer Topic reactions Ring structure NO group2 Fig re 4: Evalu tion of single-in…”
MethodInfluentialLearning Multiagent Communication with Backpropagation
Sukhbaatar, S., Szlam, A. D., & Fergus, R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.07736 · Cited by 261
“In particular, in [23], the output of the model is the fixed point of iterating equations (3) and (1) to convergence, using recurrent models.”
BackgroundSpatial-Temporal Transformer Networks for Traffic Flow Forecasting
Xu, M., Dai, W., Liu, C., Gao, X., Lin, W., Qi, G.-J., & Xiong, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.02908 · Cited by 261
“Graph neural networks (GNNs) [17] [18] are latter proposed to generalize the deep learning to non-Euclidean domain.”
BackgroundGraph Clustering with Graph Neural NetworksPreprint
Tsitsulin, A., Palowitch, J., Perozzi, B., & Müller, E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.16904 · Cited by 391
“Graph Neural Networks (GNNs) [15, 21, 29, 39, 48] allow end-toend differentable losses over data with arbitrary structure.”
BackgroundHigher-Order Explanations of Graph Neural Networks via Relevant Walks
Schnake, T., Eberle, O., Lederer, J., Nakajima, S., Schutt, K. T., Muller, K.-R., & Montavon, G. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3115452 · Cited by 259
“Graph neural networks (GNNs) [1], [2] are special types of”
BackgroundMethodGao, H., & Ji, S. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3081010 · Cited by 259
Faroughi, S. A., Pawar, N. M., Fernandes, C., Raissi, M., Das, S., Kalantari, N. K., & Kourosh Mahjour, S. (2024) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4064449 · Cited by 257
Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction
Li, Z., Cui, Z., Wu, S., Zhang, X., & Wang, L. (2019) · Proceedings of the 28th ACM International Conference on Information and Knowledge Management · doi:10.1145/3357384.3357951 · Cited by 256
“The concept of GNN is first proposed by [24].”
BackgroundLiu, D., Cui, L., & Cheng, W. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/acf390 · Cited by 256
“GNN is first proposed by Scarselli et al [57], which aims to exploit graph theory to construct neural networks.”
Badreddine, S., d'Avila Garcez, A., Serafini, L., & Spranger, M. (2022) · Artificial Intelligence · doi:10.1016/j.artint.2021.103649 · Cited by 255
“The proliferation of such approaches has prompted Henry Kautz to propose a taxonony for neurosymbolic AI in [34] (also discussed in [16]), including recent work combining neural networks with graphical models and graph neural networks [59, 3, 40], statistical relational learning [20, 56], and even verification of neur…”
BackgroundSupervised Community Detection with Line Graph Neural NetworksPreprint
Chen, Z., Li, X., & Bruna, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.08415 · Cited by 311
“The GNN was first proposed in (Scarselli et al., 2009).”
BackgroundDPGN: Distribution Propagation Graph Network for Few-Shot Learning
Yang, L., Li, L., Zhang, Z., Zhou, X., Zhou, E., & Liu, Y. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01340 · Cited by 252
Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation
Li, R., Zhang, S., Wan, B., & He, X. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01096 · Cited by 252
“The Graph Neural Network (GNN) is first proposed by [35], which is a powerful method for handling the non-Euclidean data.”
MethodDiscovering Symbolic Models from Deep Learning with Inductive Biases
Cranmer, M., Sánchez‐González, Á., Battaglia, P., Xu, R., Cranmer, K. S., Spergel, D. N., & Ho, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.11287 · Cited by 250
“Recent work has leveraged the inductive biases of Interaction Networks (INs) [6] in their generalized form, the Graph Network , a type of Graph Neural Network [7, 8, 9], to learn models of particle systems in many physical domains [6, 10, 11, 12, 13, 14, 15, 16].”
BackgroundDeep vessel segmentation by learning graphical connectivity
Shin, S. Y., Lee, S., Yun, I. D., & Lee, K. M. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101556 · Cited by 250
A Lexicon-Based Graph Neural Network for Chinese NER
Gui, T., Zou, Y., Zhang, Q., Peng, M., Fu, J., Wei, Z., & Huang, X. (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/d19-1096 · Cited by 249
“For a general graph, it is common practice to apply recurrent-based modules to update hidden representations of nodes (Scarselli et al., 2009; Li et al., 2015).”
BackgroundBiological network analysis with deep learning
Muzio, G., O’Bray, L., & Borgwardt, K. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbaa257 · Cited by 248
“While the field of GNNs encompasses many different sub-architectures, such as recurrent GNNs [84, 85], spatial-temporal GNNs [86, 87] and graph autoencoders [83], we focus here on the ones that are currently used in biological network analysis, namely graph embedding techniques [80–82] and graph…”
Learning to Drop: Robust Graph Neural Network via Topological Denoising
Luo, D., Cheng, W., Yu, W., Zong, B., Ni, J., Chen, H., & Zhang, X. (2021) · Proceedings of the 14th ACM International Conference on Web Search and Data Mining · doi:10.1145/3437963.3441734 · Cited by 248
Recurrent Independent Mechanisms
Goyal, A., Lamb, A., Hoffmann, J., Sodhani, S., Levine, S., Bengio, Y., & Schölkopf, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.10893 · Cited by 68
“Relational Graph Based Methods: Recent graph-based architectures have studied combinatorial generalization in the context of modeling dynamical systems like physics simulation, multi-object scenes, and motion-capture data, and multiagent systems (Scarselli et al., 2008; Bronstein et al., 2017; Watters et al., 2017; Ra…”
BackgroundLearning a Deep ConvNet for Multi-Label Classification With Partial Labels
Durand, T., Mehrasa, N., & Mori, G. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00074 · Cited by 245
“To model the interactions between the categories, we use a Graph Neural Network (GNN) [19, 45] on top of a ConvNet.”
MethodYu, B., Lee, Y., & Sohn, K. (2020) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2020.02.013 · Cited by 243
Interpolated Convolutional Networks for 3D Point Cloud Understanding
Mao, J., Wang, X., & Li, H. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00166 · Cited by 241
“Graph Neural Networks (GNNs) [33] have been widely used to deal with irregular data structure.”
MethodSentence-State LSTM for Text Representation
Zhang, Y., Liu, Q., & Song, L. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1030 · Cited by 239
“S-LSTM is inspired by message passing over graphs (Murphy et al., 1999; Scarselli et al., 2009).”
BackgroundD’ya Like DAGs? A Survey on Structure Learning and Causal Discovery
Vowels, M. J., Camgoz, N. C., & Bowden, R. (2023) · ACM Computing Surveys · doi:10.1145/3527154 · Cited by 237
“Examples of hybrid approaches include methods such as Recurrent Independent Mechanisms [77], graph networks [12, 13, 209], and a large body of work on scene understanding [118, 155, 170, 172, 260].”
BackgroundMethodExact Combinatorial Optimization with Graph Convolutional Neural Networks
Gasse, M., Chételat, D., Ferroni, N., Charlin, L., & Lodi, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.01629 · Cited by 237
BaGFN: Broad Attentive Graph Fusion Network for High-Order Feature Interactions
Xie, Z., Zhang, W., Sheng, B., Li, P., & Chen, C. L. P. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3116209 · Cited by 237
“GNN [32] is designed to address the above deficiencies, which is a type of neural network that performs neural network operations via graph structure to acquire node representations.”
BackgroundMethodInfluentialIterative Visual Reasoning Beyond Convolutions
Chen, X., Li, L.-J., Fei-Fei, L., & Gupta, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00756 · Cited by 236
A review of artificial intelligence applied to path planning in UAV swarms
Puente-Castro, A., Rivero, D., Pazos, A., & Fernandez-Blanco, E. (2022) · Neural Computing and Applications · doi:10.1007/s00521-021-06569-4 · Cited by 236
“Graph Neural Networks extend existing neural network methods for processing the data represented in graph domain[87].”
MethodAttention-based Graph Neural Network for Semi-supervised Learning
Thekumparampil, K. K., Wang, C., Oh, S., & Li, L.-J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.03735 · Cited by 235
“Originally introduced as extensions of recurrent neural networks, GNNs apply recurrent layers to each node with additional local averaging layer [20, 36].”
BackgroundNeural Relational Inference for Interacting Systems
Kipf, T., Fetaya, E., Wang, K.-C., Welling, M., & Zemel, R. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.04687 · Cited by 235
A Gentle Introduction to Graph Neural Networks
Sanchez-Lengeling, B., Reif, E., Pearce, A., & Wiltschko, A. (2021) · Distill · doi:10.23915/distill.00033 · Cited by 234
A Primer on Motion Capture with Deep Learning: Principles, Pitfalls, and Perspectives
Mathis, A., Schneider, S., Lauer, J., & Mathis, M. W. (2020) · Neuron · doi:10.1016/j.neuron.2020.09.017 · Cited by 231
An Overview of Deep Semi-Supervised Learning
Ouali, Y., Hudelot, C., & Tami, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.05278 · Cited by 230
“The different approaches such as GCN [137, 147, 81, 85], GraphSAGE [61] and GAT [155] follow the same procedure but differ primarily in how the aggregation, the combination and the normalization are performed.”
MethodPrincipal Neighbourhood Aggregation for Graph Nets
Corso, G., Cavalleri, L., Beaini, D., Lió, P., & Veličković, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.05718 · Cited by 230
“Graph Neural Networks (GNNs) have been an active research field for the last ten years with significant advancements in graph representation learning [1, 2, 3, 4].”
BackgroundTAGNN: Target Attentive Graph Neural Networks for Session-based Recommendation
Yu, F., Zhu, Y., Liu, Q., Wu, S., Wang, L., & Tan, T. (2020) · Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3397271.3401319 · Cited by 230
Waikhom, L., & Patgiri, R. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10321-2 · Cited by 255
“Scarselli et al. (2008) expanded the work of updating initial edges x(u,v) by conditioning the messages.”
BackgroundBertGCN: Transductive Text Classification by Combining GNN and BERT
Lin, Y., Meng, Y., Sun, X., Han, Q., Kuang, K., Li, J., & Wu, F. (2021) · Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 · doi:10.18653/v1/2021.findings-acl.126 · Cited by 228
Order Matters: Semantic-Aware Neural Networks for Binary Code Similarity Detection
Yu, Z., Cao, R., Tang, Q., Nie, S., Huang, J., & Wu, S. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i01.5466 · Cited by 228
“Graph neural networks (Scarselli et al. 2008) propose to learn the node representation and graph representation.”
BackgroundGraph Neural Network: A Comprehensive Review on Non-Euclidean Space
Asif, N. A., Sarker, Y., Chakrabortty, R. K., Ryan, M. J., Ahamed, M. H., Saha, D. K., Badal, F. R., Das, S. K., Ali, M. F., Moyeen, S. I., et al. (2021) · IEEE Access · doi:10.1109/access.2021.3071274 · Cited by 228
“These data-driven methods include different types of graph-based methods as well as some of their limitations. a: GRAPH NEURAL NETWORK Scarselli et al. [45] first introduced the graph network leveraging neural network for data exploration in the graph domain.”
MethodGraph Neural Networks for Intrusion Detection: A Survey
Bilot, T., Madhoun, N. E., Agha, K. A., & Zouaoui, A. (2023) · IEEE Access · doi:10.1109/access.2023.3275789 · Cited by 227
“TheGraphNeural Network (GNN)model [36], [37] is the origin of the first application of deep neural networks to graphstructured data.”
BackgroundA Survey on Graph Representation Learning Methods
Khoshraftar, S., & An, A. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3633518 · Cited by 226
“Type Graph Methods Trad Static Node2vec [81], Deepwalk [201], Graph Factorization [2], GraRep [27], HOPE [192], STRAP [280], HARP [35], LINE [225], SDNE [233], DNGR [28], VGAE [117], AWE [108], PRUNE [123], E[D] [1], ULGE [186], APP [316], CDE [135], GNE [58], DNE [218], DANE [71], RandNE [307], SANE [235], BANE [270]…”
MethodZhang, C., Sjarif, N. N. A., & Ibrahim, R. (2023) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1519 · Cited by 282
“GNNs are a class of deep learning models designed to operate on graph-structured data, allowing for effective representation learning and reasoning over nodes and edges in the graph (Scarselli et al., 2009).”
YOLOv1 to YOLOv10: The Fastest and Most Accurate Real-time Object Detection Systems
Wang, C.-Y., & Liao, H.-Y. M. (2024) · APSIPA Transactions on Signal and Information Processing · doi:10.1561/116.20240058 · Cited by 265
CGC-Net: Cell Graph Convolutional Network for Grading of Colorectal Cancer Histology Images
Zhou, Y., Graham, S., Alemi Koohbanani, N., Shaban, M., Heng, P.-A., & Rajpoot, N. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00050 · Cited by 225
“Graph neural network: Earlier Graph neural network methods [20, 34, 39] utilise recurrent neural networks for neighbor information propagation.”
MethodComputational Capabilities of Graph Neural Networks
Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2008.2005141 · Cited by 225
Self-citationWithnall, M., Lindelöf, E., Engkvist, O., & Chen, H. (2020) · Journal of Cheminformatics · doi:10.1186/s13321-019-0407-y · Cited by 225
“This work was later expanded upon by Micheli [12] and Scarselli et al. [13] In 2013, the Graph Convolutional Network (GCN) was presented by Bruna et al. [14] using the principles of spectral graph theory.”
MethodBresson, X., & Laurent, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.07553 · Cited by 224
“The authors extended the original LSTM model of Hochreiter & Schmidhuber (1997) to a tree-graph structure: where Unlike Scarselli et al. (2009); Li et al. (2016), Tree-LSTM does not require an iterative process to update its feature vector h i as the tree structure is also a directed acyclic graph (DAG) as original LS…”
BackgroundMethodInfluentialGraph Neural Networks with Heterophily
Zhu, J., Rossi, R. A., Rao, A., Mai, T., Lipka, N., Ahmed, N. K., & Koutra, D. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i12.17332 · Cited by 224
Geometric deep learning for computational mechanics Part I: anisotropic hyperelasticity
Vlassis, N. N., Ma, R., & Sun, W. (2020) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2020.113299 · Cited by 224
Graph HyperNetworks for Neural Architecture SearchPreprint
Zhang, C., Ren, M., & Urtasun, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.05749 · Cited by 233
“Graph Neural Network: A graph neural network (Scarselli et al., 2009; Li et al., 2016; Kipf & Welling, 2017) is a collection of nodes and edges ( V , E ) , where each node is a recurrent neural network (RNN) that individually sends and receives messages along the edges, spanning over the The GHN is…”
BackgroundCollaborative Perception in Autonomous Driving: Methods, Datasets, and Challenges
Han, Y., Zhang, H., Li, H., Jin, Y., Lang, C., & Li, Y. (2023) · IEEE Intelligent Transportation Systems Magazine · doi:10.1109/mits.2023.3298534 · Cited by 222
“Graph Neural Networks (GNNs) have the ability to process graphstructured data, which can propagate and aggregate messages from neighbors [58].”
BackgroundZhang, D., Stewart, E., Entezami, M., Roberts, C., & Yu, D. (2020) · Measurement · doi:10.1016/j.measurement.2020.107585 · Cited by 222
Sparse Graph Attention Networks
Ye, Y., & Ji, S. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3072345 · Cited by 221
“These methods can be classified into two categories based on how they manipulate the adjacent matrix: (1) spectral graph convolution networks [8], [9], [10], and (2) neighbor aggregation or message passing algorithms [11], [12], [13].”
BackgroundMethodUnveiling the potential of Graph Neural Networks for network modeling and optimization in SDN
Rusek, K., Suárez-Varela, J., Mestres, A., Barlet-Ros, P., & Cabellos-Aparicio, A. (2019) · Proceedings of the 2019 ACM Symposium on SDN Research · doi:10.1145/3314148.3314357 · Cited by 221
Auto-GNN: Neural architecture search of graph neural networks
Zhou, K., Huang, X. X., Song, Q., Chen, R., & Hu, X. (2022) · Frontiers in Big Data · doi:10.3389/fdata.2022.1029307 · Cited by 245
“he graph neural networks and neural architecture search. Graph Neural Networks. A wide variety of GNNs have been proposed to learn the node representation effectively, e.g., recursive neural networks [1, 2], graph convolutional networks [9, 30–32, 37] and graph attention networks [10, 28]. Most of these approaches are…”
BackgroundMethodA Survey on The Expressive Power of Graph Neural NetworksPreprint
Sato, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.04078 · Cited by 241
“Graph neural networks (GNNs) (Gori et al., 2005; Scarselli et al., 2009) are effective machine learning models for various graph-related problems, including chemo-informatics (Gilmer et al.”
BackgroundInfluentialSpatial-Temporal Residential Short-Term Load Forecasting via Graph Neural Networks
Lin, W., Wu, D., & Boulet, B. (2021) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2021.3093515 · Cited by 218
News recommender system: a review of recent progress, challenges, and opportunities
Raza, S., & Ding, C. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10043-x · Cited by 217
Deep learning-based 3D point cloud classification: A systematic survey and outlook
Zhang, H., Wang, C., Tian, S., Lu, B., Zhang, L., Ning, X., & Bai, X. (2023) · Displays · doi:10.1016/j.displa.2023.102456 · Cited by 217
“Anisotropic spatial geometry is constructed in the point cloud to implement depthwise separable convolution, replacing depthwise convolution with the spatial coverage operator (SCOP). c) 3: Graph-based methods The graph neural network (GNN) was first proposed by Scarselli et al. [70].”
MethodDirectional Message Passing for Molecular GraphsPreprint
Klicpera, J., Groß, J., & Günnemann, S. (2020) · arXiv (Cornell University) · Cited by 380
A syntax-guided edit decoder for neural program repair
Zhu, Q., Sun, Z., Xiao, Y.-A., Zhang, W., Yuan, K., Xiong, Y., & Zhang, L. (2021) · Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3468264.3468544 · Cited by 216
Graph representation learning in bioinformatics: trends, methods and applications
Yi, H.-C., You, Z.-H., Huang, D.-S., & Kwoh, C. K. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbab340 · Cited by 216
Application of deep learning methods in biological networks
Jin, S., Zeng, X., Xia, F., Huang, W., & Liu, X. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbaa043 · Cited by 216
Disentangled Graph Convolutional Networks
Ma, J., Cui, P., Kuang, K., Wang, X., & Zhu, W. (2019) · International Conference on Machine Learning · Cited by 465
Robot learning towards smart robotic manufacturing: A review
Liu, Z., Liu, Q., Xu, W., Wang, L., & Zhou, Z. (2022) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2022.102360 · Cited by 215
Routing optimization meets Machine Intelligence: A perspective for the future network
Dai, B., Cao, Y., Wu, Z., Dai, Z., Yao, R., & Xu, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.06.093 · Cited by 215
Hirohara, M., Saito, Y., Koda, Y., Sato, K., & Sakakibara, Y. (2018) · BMC Bioinformatics · doi:10.1186/s12859-018-2523-5 · Cited by 214
Phase-Locking Value Based Graph Convolutional Neural Networks for Emotion Recognition
Wang, Z., Tong, Y., & Heng, X. (2019) · IEEE Access · doi:10.1109/access.2019.2927768 · Cited by 214
“In order to efficiently extract spatial features for machine learning on such data structures (topologies), Graph neural network (GNN) [25] has become the focus of research.”
BackgroundGraphiT: Encoding Graph Structure in TransformersPreprint
Mialon, G., Chen, D., Selosse, M., & Mairal, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.05667 · Cited by 276
“Originally introduced in [28], GNNs have been derived as an extension of convolutions for graph-structured data: they use a message passing paradigm in which vectors (messages) are exchanged (passed) between neighboring nodes whose representations are updated using neural networks.”
BackgroundMethodA survey on Deep Learning Advances on Different 3D Data RepresentationsPreprint
Ahmed, E., Saint, A., Shabayek, A. E. R., Cherenkova, K., Das, R., Gusev, G., Aouada, D., & Ottersten, B. (2018) · arXiv (Cornell University) · doi:10.13140/rg.2.2.32083.02080 · Cited by 241
Benchmarking Graph Neural Networks
Dwivedi, V. P., Joshi, C. K., Luu, A. T., Laurent, T., Bengio, Y., & Bresson, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00982 · Cited by 211
“PATTERN: The graph pattern recognition task, presented in [75], aims at finding a fixed graph pattern P embedded in larger graphs G of variable sizes.”
BackgroundMethodInfluentialLGGNet: Learning From Local-Global-Graph Representations for Brain–Computer Interface
Ding, Y., Robinson, N., Tong, C., Zeng, Q., & Guan, C. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3236635 · Cited by 211
“Graph Neural Networks (GNNs) [37] were proposed to deal with the graph structured data.”
BackgroundAdversarial Graph Augmentation to Improve Graph Contrastive LearningPreprint
Suresh, S., Pan, L., Hao, C., & Neville, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.05819 · Cited by 353
“Graph neural networks (GNNs), inheriting the power of neural networks [4,5], have become the almost de facto encoders for GRL [6–9].”
BackgroundGallicchio, C., & Micheli, A. (2010) · The 2010 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2010.5596796 · Cited by 210
“Note that the accuracy of GNNs is available in [13] only for the full description AB+C+PS.”
BackgroundMethodInfluentialCellCharter reveals spatial cell niches associated with tissue remodeling and cell plasticity
Varrone, M., Tavernari, D., Santamaria-Martínez, A., Walsh, L. A., & Ciriello, G. (2024) · Nature Genetics · doi:10.1038/s41588-023-01588-4 · Cited by 210
“…hidden Markov random fields (HMRF 25 ), which extend hidden Markov models to an unbounded number of neighbors, or graph neural networks (GNNs 26 ), a machine learning technique that generates representations of a node (for example, a cell) from the convolution of features of its neighbors…”
LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting
Zeng, W., Liang, M., Liao, R., & Urtasun, R. (2021) · 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636035 · Cited by 210
“Graph Neural Networks: Relying on operators like graph convolution and message passing, graph neural networks (GNNs) and their variants [45, 5, 28, 24, 19, 31] generalize deep learning on regular graphs like grids to ones with irregular topologies.”
BackgroundA Survey of Natural Language Generation
Dong, C., Li, Y., Gong, H., Chen, M., Li, J., Shen, Y., & Yang, M. (2023) · ACM Computing Surveys · doi:10.1145/3554727 · Cited by 149
“The graph neural network (GNN) [109] is used to process the data in graph form,which can capture the dependency information between nodes of a graph via message passing.”
MethodInfluentialVerdon, G., McCourt, T., Luzhnica, E., Singh, V., Leichenauer, S., & Hidary, J. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.12264 · Cited by 52
“[10] and [11] developed methods that learned node representations by propagating the information of neighbouring nodes.”
MethodExploiting Semantics in Neural Machine Translation with Graph Convolutional Networks
Marcheggiani, D., Bastings, J., & Titov, I. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2078 · Cited by 209
Streaming Graph Neural Networks
Ma, Y., Guo, Z., Ren, Z., Tang, J., & Yin, D. (2020) · Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3397271.3401092 · Cited by 209
“ecent years, many efforts have been made to extend deep neural network models to graph structured data. These neural network models that are applied to graphs are known as graph neural network models [12, 28]. They have been applied to various tasks in many areas. Various graph neural network models have been designed…”
InfluentialObject-Centric Learning with Slot Attention
Locatello, F., Weissenborn, D., Unterthiner, T., Mahendran, A., Heigold, G., Uszkoreit, J., Dosovitskiy, A., & Kipf, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.15055 · Cited by 208
“[54] Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini.”
BackgroundInductive Representation Learning in Temporal Networks via Causal Anonymous WalksPreprint
Wang, Y., Chang, Y., Liu, Y., Leskovec, J., & Pan, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.05974 · Cited by 422
“Prior work on representation learning of temporal networks preprocesses the networks by simply aggregating the sequence of links within consecutive time windows into network snapshots, and use graph neural networks (GNN) (Scarselli et al., 2008; Kipf & Welling, 2017) and RNNs or transformer networks (Vaswani et al.”
MethodInfluentialA Graph Neural Network-Based Digital Twin for Network Slicing Management
Wang, H., Wu, Y., Min, G., & Miao, W. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3047843 · Cited by 207
“Kasgari et al. [20] Extending Deep Learning (DL) [8] operating on data represented in a graph structure has been investigated under the umbrella of GNN [21], and has attracted a significant amount of research efforts in recent years [22].”
BackgroundLGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations
Cao, R., Chen, L., Chen, Z., Zhao, Y., Zhu, S., & Yu, K. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.198 · Cited by 138
“Typically, previous literature utilizes a node-centric graph neural network (GNN, Scarselli et al., 2008) ∗ The corresponding authors are Lu Chen and Kai Yu. to aggregate information from neighboring nodes.”
MethodInductive Matrix Completion Based on Graph Neural NetworksPreprint
Zhang, M., & Chen, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.12058 · Cited by 268
“By feeding these enclosing subgraphs to a graph neural network (GNN) [8, 19, 31, 37], we train a graph regression model that maps a subgraph to the rating of its target link.”
Method
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.