nach oben

Erschienen in:

2022 | OriginalPaper | Buchkapitel

wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction

verfasst von : Marco Grassia, Giuseppe Mangioni

Erschienen in: Complex Networks & Their Applications X

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Graph Neural Networks (GNNs) have been widely used to learn representations on graphs and tackle many real-world problems from a wide range of domains. In this paper we propose wsGAT, an extension of the Graph Attention Network (GAT) [24] layers, meant to address the lack of GNNs that can handle graphs with signed and weighted links, which are ubiquitous, for instance, in trust and correlation networks. We first evaluate the performance of our proposal by comparing against GCNII [6] in the weighed link prediction task, and against SGCN [8] in the link sign prediction task. After that, we combine the two tasks and show their performance on predicting the signed weight of links, and their existence. Our results on real-world networks show that models with wsGAT layers outperform the ones with GCNII and SGCN layers, and that there is no loss in performance when signed weights are predicted.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel CoVerD: Community-Based Vertex Defense Against Crawling Adversaries

Nächstes Kapitel Link Predictability Classes in Complex Networks

Bachi, G., Coscia, M., Monreale, A., Giannotti, F.: Classifying trust/distrust relationships in online social networks. In: 2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Confernece on Social Computing, pp. 552–557. IEEE (2012)

Bang-Jensen, J., Gutin, G.Z.: Digraphs: Theory, Algorithms and Applications. Springer Science & Business Media, Heidelberg (2008)

Borgatti, S.P., Everett, M.G., Johnson, J.C.: Analyzing Social Networks. Sage, Thousand Oaks (2018)

Carchiolo, V., Longheu, A., Malgeri, M., Mangioni, G.: Trust assessment: a personalized, distributed, and secure approach. Concurr. Comput. Pract. Exp. 24(6), 605–617 (2012)CrossRefMATH

Carchiolo, V., Longheu, A., Malgeri, M., Mangioni, G.: Users’ attachment in trust networks: reputation vs. effort. Int. J. Bio-Inspired Comput. 5(4), 199–209 (2013)

Chen, M., Wei, Z., Huang, Z., Ding, B., Li, Y.: Simple and deep graph convolutional networks (2020)

Chen, Z.J., He, Y., Rosa-Neto, P., Germann, J., Evans, A.C.: Revealing modular architecture of human brain structural networks by using cortical thickness from mri. Cereb. Cortex 18(10), 2374–2381 (2008)CrossRef

Derr, T., Ma, Y., Tang, J.: Signed graph convolutional network (2018)

Fey, M., Lenssen, J.E.: Fast graph representation learning with PyTorch Geometric. In: ICLR Workshop on Representation Learning on Graphs and Manifolds (2019)

10.

Grassia, M., De Domenico, M., Mangioni, G.: Machine learning dismantling and early-warning signals of disintegration in complex systems. Nat. Commun. 12(1), 5190 (2021). https://doi.org/10.1038/s41467-021-25485-8

11.

Grassia, M., Lauri, J., Dutta, S., Ajwani, D.: Learning multi-stage sparsification for maximum clique enumeration. arXiv preprint arXiv:1910.00517 (2019)

12.

Hamilton, W.L.: Graph representation learning. Synth. Lect. Artif. Intell. Mach. Learn. 14(3), 1–159 (2020)

13.

Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks (2017)

14.

Kumar, S., Spezzano, F., Subrahmanian, V.S., Faloutsos, C.: Edge weight prediction in weighted signed networks. In: 2016 IEEE 16th International Conference on Data Mining (ICDM), pp. 221–230 (2016)

15.

Kunegis, J., Schmidt, S., Lommatzsch, A., Lerner, J., Luca, E.W.D., Albayrak, S.: Spectral analysis of signed graphs for clustering, prediction and visualization, pp. 559–570 (2010). https://doi.org/10.1137/1.9781611972801.49

16.

Leskovec, J., Huttenlocher, D., Kleinberg, J.: Signed networks in social media. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 1361–1370 (2010)

17.

Massa, P., Salvetti, M., Tomasoni, D.: Bowling alone and trust decline in social network sites. In: 2009 Eighth IEEE International Conference on Dependable, Autonomic and Secure Computing, pp. 658–663 (2009)

18.

Massa, P., Avesani, P.: Controversial users demand local trust metrics: an experimental study on epinions.com community. In: Proceedings of the American Association for Artificial Intelligence Conference, pp. 121–126 (2005)

19.

Mizuno, T., Takayasu, H., Takayasu, M.: Correlation networks among currencies. Phys. A 364, 336–342 (2006)CrossRef

20.

Newman, M.E.: The structure and function of complex networks. SIAM Rev. 45(2), 167–256 (2003)MathSciNetCrossRefMATH

21.

Newman, M.E.: Analysis of weighted networks. Phys. Rev. E 70(5), 056131 (2004)

22.

Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Netw. 20(1), 61–80 (2008)CrossRef

23.

Vaswani, A., et al.: Attention is all you need (2017)

24.

Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks (2018)

25.

Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Philip, S.Y.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32 (2020)

26.

Zhou, J., et al.: Graph neural networks: a review of methods and applications. AI Open 1, 57–81 (2020)CrossRef

Titel: wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction
verfasst von: Marco Grassia
Giuseppe Mangioni
Verlag: Springer International Publishing
Buch: Complex Networks & Their Applications X
Print ISBN: 978-3-030-93408-8

Electronic ISBN: 978-3-030-93409-5

Copyright-Jahr: 2022
DOI: https://doi.org/10.1007/978-3-030-93409-5_31

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner