Skip to main content
Top
Published in:

01-12-2020 | Original Article

t-PINE: tensor-based predictable and interpretable node embeddings

Authors: Saba Al-Sayouri, Ekta Gujral, Danai Koutra, Evangelos E. Papalexakis, Sarah S. Lam

Published in: Social Network Analysis and Mining | Issue 1/2020

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Graph representations have increasingly grown in popularity during the last years. Existing representation learning approaches explicitly encode network structure. Despite their good performance in downstream processes (e.g., node classification, link prediction), there is still room for improvement in different aspects, such as efficacy, visualization, and interpretability. In this paper, we propose, t-PINE, a method that addresses these limitations. Contrary to baseline methods, which generally learn explicit graph representations by solely using an adjacency matrix, t-PINE avails a multi-view information graph—the adjacency matrix represents the first view, and a nearest neighbor adjacency, computed over the node features, is the second view—in order to learn explicit and implicit node representations, using the Canonical Polyadic (a.k.a. CP) decomposition. We argue that the implicit and the explicit mapping from a higher-dimensional to a lower-dimensional vector space is the key to learn more useful, highly predictable, and gracefully interpretable representations. Having good interpretable representations provides a good guidance to understand how each view contributes to the representation learning process. In addition, it helps us to exclude unrelated dimensions. Extensive experiments show that t-PINE drastically outperforms baseline methods by up to 351.5% with respect to Micro-F1, in several multi-label classification problems, while it has high visualization and interpretability utility.

Dont have a licence yet? Then find out more about our products and how to get one now:

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!

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!

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!

Literature
go back to reference Aivazoglou M, Roussos AO, Margaris D, Vassilakis C, Ioannidis S, Polakis J, Spiliotopoulos D (2020) A fine-grained social network recommender system. Soc Netw Anal Min 10(1):8CrossRef Aivazoglou M, Roussos AO, Margaris D, Vassilakis C, Ioannidis S, Polakis J, Spiliotopoulos D (2020) A fine-grained social network recommender system. Soc Netw Anal Min 10(1):8CrossRef
go back to reference Azaouzi M, Rhouma D, Romdhane LB (2019) Community detection in large-scale social networks: state-of-the-art and future directions. Soc Netw Anal Min 9(1):23CrossRef Azaouzi M, Rhouma D, Romdhane LB (2019) Community detection in large-scale social networks: state-of-the-art and future directions. Soc Netw Anal Min 9(1):23CrossRef
go back to reference Bhagat S, Cormode G, Muthukrishnan S (2011) Node classification in social networks. In: Social network data analytics. Springer, pp 115–148 Bhagat S, Cormode G, Muthukrishnan S (2011) Node classification in social networks. In: Social network data analytics. Springer, pp 115–148
go back to reference Cao B, He L, Wei X, Xing M, Yu PS, Klumpp H, Leow AD (2017) t-BNE: tensor-based brain network embedding. In: Proceedings of the 2017 SIAM international conference on data mining. SIAM, pp 189–197 Cao B, He L, Wei X, Xing M, Yu PS, Klumpp H, Leow AD (2017) t-BNE: tensor-based brain network embedding. In: Proceedings of the 2017 SIAM international conference on data mining. SIAM, pp 189–197
go back to reference Carroll JD, Chang JJ (1970) Analysis of individual differences in multidimensional scaling via an n-way generalization of “eckart-youn” decomposition. Psychometrika 35(3):283–319CrossRef Carroll JD, Chang JJ (1970) Analysis of individual differences in multidimensional scaling via an n-way generalization of “eckart-youn” decomposition. Psychometrika 35(3):283–319CrossRef
go back to reference Derr T, Wang Z, Dacon J, Tang J (2020) Link and interaction polarity predictions in signed networks. Soc Netw Anal Min 10(1):1–14CrossRef Derr T, Wang Z, Dacon J, Tang J (2020) Link and interaction polarity predictions in signed networks. Soc Netw Anal Min 10(1):1–14CrossRef
go back to reference Dhillon IS, Modha DS (2001) Concept decompositions for large sparse text data using clustering. Mach Learn 42(1–2):143–175CrossRef Dhillon IS, Modha DS (2001) Concept decompositions for large sparse text data using clustering. Mach Learn 42(1–2):143–175CrossRef
go back to reference Easley D, Kleinberg J (2010) Networks, crowds, and markets: reasoning about a highly connected world. Cambridge University Press, CambridgeCrossRef Easley D, Kleinberg J (2010) Networks, crowds, and markets: reasoning about a highly connected world. Cambridge University Press, CambridgeCrossRef
go back to reference Gong H, Bhat S, Viswanath P (2017) Tensor-based preposition representation Gong H, Bhat S, Viswanath P (2017) Tensor-based preposition representation
go back to reference Goyal P, Ferrara E (2017) Graph embedding techniques, applications, and performance: a survey. arXiv preprint arXiv:1705.02801 Goyal P, Ferrara E (2017) Graph embedding techniques, applications, and performance: a survey. arXiv preprint arXiv:1705.02801
go back to reference Grover A, Leskovec J (2016) node2vec: Scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 855–864 Grover A, Leskovec J (2016) node2vec: Scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 855–864
go back to reference Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. In: Advances in neural information processing systems, pp 1024–1034 Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. In: Advances in neural information processing systems, pp 1024–1034
go back to reference Liben-Nowell D, Kleinberg J (2007) The link-prediction problem for social networks. J Assoc Inf Sci Technol 58(7):1019–1031CrossRef Liben-Nowell D, Kleinberg J (2007) The link-prediction problem for social networks. J Assoc Inf Sci Technol 58(7):1019–1031CrossRef
go back to reference Lu Q, Getoor L (2003) Link-based classification. In: Proceedings of the 20th international conference on machine learning (ICML-03), pp 496–503 Lu Q, Getoor L (2003) Link-based classification. In: Proceedings of the 20th international conference on machine learning (ICML-03), pp 496–503
go back to reference Papalexakis EE, Faloutsos C, Sidiropoulos ND (2017) Tensors for data mining and data fusion: models, applications, and scalable algorithms. ACM Trans Intell Syst Technol (TIST) 8(2):16 Papalexakis EE, Faloutsos C, Sidiropoulos ND (2017) Tensors for data mining and data fusion: models, applications, and scalable algorithms. ACM Trans Intell Syst Technol (TIST) 8(2):16
go back to reference Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: Online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, pp 701–710 Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: Online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, pp 701–710
go back to reference Perozzi B, Kulkarni V, Skiena S (2016) Walklets: multiscale graph embeddings for interpretable network classification. arXiv preprint arXiv:1605.02115 Perozzi B, Kulkarni V, Skiena S (2016) Walklets: multiscale graph embeddings for interpretable network classification. arXiv preprint arXiv:1605.02115
go back to reference Rossi RA, Zhou R, Ahmed NK (2017) Deep feature learning for graphs. arXiv preprint arXiv:1704.08829 Rossi RA, Zhou R, Ahmed NK (2017) Deep feature learning for graphs. arXiv preprint arXiv:1704.08829
go back to reference Smith S, Choi JW, Li J, Vuduc R, Park J, Liu X, Karypis G (2017) FROSTT: the formidable repository of open sparse tensors and tools. http://frostt.io/ Smith S, Choi JW, Li J, Vuduc R, Park J, Liu X, Karypis G (2017) FROSTT: the formidable repository of open sparse tensors and tools. http://​frostt.​io/​
go back to reference Tang J, Qu M, Wang M, Zhang M, Yan J, Mei Q (2015) Line: Large-scale information network embedding. In: Proceedings of the 24th international conference on world wide web. ACM, pp 1067–1077 Tang J, Qu M, Wang M, Zhang M, Yan J, Mei Q (2015) Line: Large-scale information network embedding. In: Proceedings of the 24th international conference on world wide web. ACM, pp 1067–1077
go back to reference Van de Cruys T (2010) A non-negative tensor factorization model for selectional preference induction. Nat Lang Eng 16(4):417–437CrossRef Van de Cruys T (2010) A non-negative tensor factorization model for selectional preference induction. Nat Lang Eng 16(4):417–437CrossRef
go back to reference Xie P (2017) Diversity-promoting and large-scale machine learning for healthcare. Ph.D. thesis, Carnegie Mellon University Pittsburgh Xie P (2017) Diversity-promoting and large-scale machine learning for healthcare. Ph.D. thesis, Carnegie Mellon University Pittsburgh
go back to reference Yang C, Liu Z, Zhao D, Sun M, Chang EY (2015) Network representation learning with rich text information. In: IJCAI, pp 2111–2117 Yang C, Liu Z, Zhao D, Sun M, Chang EY (2015) Network representation learning with rich text information. In: IJCAI, pp 2111–2117
go back to reference Yu X, Ren X, Sun Y, Gu Q, Sturt B, Khandelwal U, Norick B, Han J (2014) Personalized entity recommendation: a heterogeneous information network approach. In: Proceedings of the 7th ACM international conference on web search and data mining. ACM, pp 283–292 Yu X, Ren X, Sun Y, Gu Q, Sturt B, Khandelwal U, Norick B, Han J (2014) Personalized entity recommendation: a heterogeneous information network approach. In: Proceedings of the 7th ACM international conference on web search and data mining. ACM, pp 283–292
go back to reference Zhao B, Sen P, Getoor L (2006) Event classification and relationship labeling in affiliation networks. In: Proceedings of the workshop on statistical network analysis (SNA) at the 23rd international conference on machine learning (ICML) Zhao B, Sen P, Getoor L (2006) Event classification and relationship labeling in affiliation networks. In: Proceedings of the workshop on statistical network analysis (SNA) at the 23rd international conference on machine learning (ICML)
Metadata
Title
t-PINE: tensor-based predictable and interpretable node embeddings
Authors
Saba Al-Sayouri
Ekta Gujral
Danai Koutra
Evangelos E. Papalexakis
Sarah S. Lam
Publication date
01-12-2020
Publisher
Springer Vienna
Published in
Social Network Analysis and Mining / Issue 1/2020
Print ISSN: 1869-5450
Electronic ISSN: 1869-5469
DOI
https://doi.org/10.1007/s13278-020-00649-4

Premium Partner