Journals / EMO Bilimsel Dergi / 2023 / Cilt: 13 Sayı: 2

An Overview of Graph Neural Networks

Grafik Sinir Ağlarına Genel Bir Bakış

Pages
39–56
Publication Date
2023-07-19
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

In the study, the developed models are examined by referring to the design steps of a GNN model, and the strengths and weaknesses of GNN models against CNN and recurrent neural networks (RNN) effective models are shown.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Graph neural networks (GNN) are a deep learning method that belongs to the artificial neural network (ANN) family and performs information extraction from graphs.
📊
Key Findings & Data:It was first used in 2008 and its development started in 2014 and onwards.
💡
Conclusion & Impact:In the study, the developed models are examined by referring to the design steps of a GNN model, and the strengths and weaknesses of GNN models against CNN and recurrent neural networks (RNN) effective models are shown.
🔬Design:Review & Systematic Survey
📍Scope:2008 Verileri
⚙️Variables:Grafik Sinir Ağları · Yapay Sinir Ağları · Derin Öğrenme

Abstract

Graph neural networks (GNN) are a deep learning method that belongs to the artificial neural network (ANN) family and performs information extraction from graphs. It was first used in 2008 and its development started in 2014 and onwards. GNNs, which were developed in response to the failure of convolutional neural networks (CNN) to meet the expected performance on visuals, are used in many fields such as physics, chemistry, biology and cyber security. In this study, GNNs and their models are basically explained and a comprehensive literature review is carried out. In the study, the developed models are examined by referring to the design steps of a GNN model, and the strengths and weaknesses of GNN models against CNN and recurrent neural networks (RNN) effective models are shown.

Özet

Grafik sinir ağları (GNN), yapay sinir ağı (ANN) ailesine mensup ve grafikler üzerinden bilgi çıkarımı işlemi gerçekleştiren bir derin öğrenme yöntemidir. İlk kullanımı 2008 yılında gerçekleşmiş, gelişimi ise 2014 yılı ve sonrasında olmuştur. Evrişimli sinir ağlarının (CNN) görseller üzerinde beklenen performansı karşılamamasına karşılık olarak geliştirilen GNN’ler; fizik, kimya, biyoloji, siber güvenlik gibi birçok alanda kullanılmaktadır. Bu çalışmada GNN’ler ve modelleri temel olarak anlatılmış ve kapsamlı bir literatür taraması gerçekleştirilmiştir. Çalışma içerisinde bir GNN modelinin tasarım adımlarına değinilerek geliştirilen modeller incelenmiş, GNN modellerinin CNN ve yinelemeli sinir ağları (RNN) etkili modellere karşı güçlü ve zayıf yönleri gösterilmiştir.

🔖

Cite This Article

GÜMÜŞ, H. T., EYÜPOĞLU, C. (2023). An Overview of Graph Neural Networks. EMO Bilimsel Dergi, Cilt: 13 Sayı: 2, 39–56. https://ajindex.com/articles/955263

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (1)

  1. Referans1 D.H. Hubel, T.N. Wiesel, “Receptive fields, binocular interaction and functional architecture in the cat's visual cortex.” J Physiol. 1962 Jan; vol. 160, no. 1, pp. 106–154.2, 1962. Referans2 A. Sperduti, A. Starita, “Supervised neural networks for the classification of structures.” in IEEE Transactions on Neural Networks, vol. 8, no. 3, pp. 714-735, May 1997 Referans3 F. Scarselli, M. Gori, A.C Tsoi, M. Hagenbuchner, G. Monfardini, “The Graph Neural Network Model.” IEEE Transactions on Neural Networks, vol. 20, no. 1, pp. 61-80. 2019. Referans4 M. Gori, G. Monfardini, F.A. Scarsell, “New Model for Learning in Graph Domains.” Proceedings. 2005 IEEE International Joint Conference on Neural Networks, vol. 2, pp. 729-734, 2005. Referans5 M. Gori, M. Maggini, L. Sarti, “A recursive neural network model for processing directed acyclic graphs with labeled edges.” in Proceedings of the International Joint Conference on Neural Networkss, Portland (USA), pp. 1351–1355, July 2003. Referans6 Z. Chen, J. Xu, C. Alippi, S.X. Ding, Y. Shardt, T. Peng, C. Yang, C. “Graph neural network-based fault diagnosis: a Review.” ArXiv. 2021 Referans7 J. Zhou, et. Al., “Graph neural networks: A review of methods and applications.” Al Open. Vol. 1, p.57-81, 2020. Referans8 N.A. Asıf, Y. Sarker, R.K. Chakrabbortty, M.J. Ryan, H. Ahamed, D.K., Saha, F.R. Badal, S.K. Das, F. Alı, S.I Moyeen, R. Islam, Z. Tasneemi “Graph Neural Network: A Comprehensive Review on Non-Euclidean Space.” April 27, 2021. Referans9 M.M. Bronstein, J. Bruna, Y. LeCun, A. Szlam, P. Vandergheynst, “Geometric deep learning: going beyond Euclidean data.” IEEE SIG PROC MAG, 2017 Referans10 Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, P.S. Yu, “A Comprehensive Survey on Graph Neural Networks.” Journal Of Latex Class Fıles, Vol. 32, No. 1, pp. 4-24, August 2019 Referans11 M. Kampffmeyer, Y. Chen, X. Liang, H. Wang, Y. Zhang, E.R. Xing, “Rethinking Knowledge Graph Propagation for Zero-Shot Learning.” CVPR 2019 Referans12 Z. Hu, Y. Dong, K. Wang, Y. Sun, Y. “Heterogeneous graph transformer.” In: Proceedings of WWW, 2020, pp. 2704–2710 Referans13 C. Zhang, D. Song, C. Huang, A. Swami, N.V. Chawla, “Heterogeneous graph neural network.” In: Proceedings of KDD. 2019, pp. 793–803. Referans14 M. Schlichtkrull, T.N. Kipf, P. Bloem, R. van den Berg, I. Titov, M. Welling, “Modeling relational data with graph convolutional networks.” In: Proceedings of ESWC. Springer, 2018, pp. 593–607. Referans15 D. Beck, G. Haffari, T.