Skip to main content

2022 | OriginalPaper | Buchkapitel

HyperNetVec: Fast and Scalable Hierarchical Embedding for Hypergraphs

verfasst von : Sepideh Maleki, Donya Saless, Dennis P. Wall, Keshav Pingali

Erschienen in: Network Science

Verlag: Springer International Publishing

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

search-config
loading …

Abstract

Many problems such as node classification and link prediction in network data can be solved using graph embeddings. However, it is difficult to use graphs to capture non-binary relations such as communities of nodes. These kinds of complex relations are expressed more naturally as hypergraphs. While hypergraphs are a generalization of graphs, state-of-the-art graph embedding techniques are not adequate for solving prediction and classification tasks on large hypergraphs accurately in reasonable time. In this paper, we introduce HyperNetVec, a novel hierarchical framework for scalable unsupervised hypergraph embedding. HyperNetVec exploits shared-memory parallelism and is capable of generating high quality embeddings for real-world hypergraphs with millions of nodes and hyperedges in only a couple of minutes while existing hypergraph systems either fail for such large hypergraphs or may take days to produce the embeddings.

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!

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!

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!

Literatur
2.
Zurück zum Zitat Bordes, A., Usunier, N., Garcia-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Proceedings of the 26th International Conference on Neural Information Processing Systems (2013) Bordes, A., Usunier, N., Garcia-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Proceedings of the 26th International Conference on Neural Information Processing Systems (2013)
3.
Zurück zum Zitat Bui, T.N., Jones, C.: A heuristic for reducing fill-in in sparse matrix factorization. In: SIAM Conference on Parallel Processing for Scientific Computing, March 1993 Bui, T.N., Jones, C.: A heuristic for reducing fill-in in sparse matrix factorization. In: SIAM Conference on Parallel Processing for Scientific Computing, March 1993
4.
Zurück zum Zitat Chen, H., Perozzi, B., Hu, Y., Skiena, S.: Harp: Hierarchical representation learning for networks (2017) Chen, H., Perozzi, B., Hu, Y., Skiena, S.: Harp: Hierarchical representation learning for networks (2017)
6.
Zurück zum Zitat Deng, C., Zhao, Z., Wang, Y., Zhang, Z., Feng, Z.: Graphzoom: a multi-level spectral approach for accurate and scalable graph embedding (2020) Deng, C., Zhao, Z., Wang, Y., Zhang, Z., Feng, Z.: Graphzoom: a multi-level spectral approach for accurate and scalable graph embedding (2020)
9.
Zurück zum Zitat Feng, Y., You, H., Zhang, Z., Ji, R., Gao, Y.: Hypergraph neural networks (2019) Feng, Y., You, H., Zhang, Z., Ji, R., Gao, Y.: Hypergraph neural networks (2019)
11.
Zurück zum Zitat Giurgiu, M., et al.: CORUM: the comprehensive resource of mammalian protein complexes-2019. Nucl. Acids Res. (2019) Giurgiu, M., et al.: CORUM: the comprehensive resource of mammalian protein complexes-2019. Nucl. Acids Res. (2019)
13.
Zurück zum Zitat Grover, A., Leskovec, J.: node2vec: Scalable feature learning for networks (2016) Grover, A., Leskovec, J.: node2vec: Scalable feature learning for networks (2016)
14.
Zurück zum Zitat Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs (2018) Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs (2018)
16.
Zurück zum Zitat Karypis, G., Aggarwal, R., Kumar, V., Shekhar, S.: Multilevel hypergraph partitioning: applications in VLSI domain. IEEE Trans. Very Large Scale Integr. Syst. (1999) Karypis, G., Aggarwal, R., Kumar, V., Shekhar, S.: Multilevel hypergraph partitioning: applications in VLSI domain. IEEE Trans. Very Large Scale Integr. Syst. (1999)
18.
Zurück zum Zitat Li, Q., Han, Z., Wu, X.M.: Deeper insights into graph convolutional networks for semi-supervised learning (2018) Li, Q., Han, Z., Wu, X.M.: Deeper insights into graph convolutional networks for semi-supervised learning (2018)
19.
Zurück zum Zitat Liang, J., Gurukar, S., Parthasarathy, S.: Mile: a multi-level framework for scalable graph embedding (2020) Liang, J., Gurukar, S., Parthasarathy, S.: Mile: a multi-level framework for scalable graph embedding (2020)
21.
Zurück zum Zitat Mateev, N., Pingali, K., Stodghill, P., Kotlyar, V.: Next-generation generic programming and its application to sparse matrix computations. In: Proceedings of the 14th International Conference on Supercomputing. ICS 2000, pp. 88–99. Association for Computing Machinery, New York (2000) Mateev, N., Pingali, K., Stodghill, P., Kotlyar, V.: Next-generation generic programming and its application to sparse matrix computations. In: Proceedings of the 14th International Conference on Supercomputing. ICS 2000, pp. 88–99. Association for Computing Machinery, New York (2000)
22.
Zurück zum Zitat Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD 2014. ACM, New York (2014) Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD 2014. ACM, New York (2014)
23.
Zurück zum Zitat Pingali, K., et al.: The tao of parallelism in algorithms. In: PLDI 2011, pp. 12–25 (2011) Pingali, K., et al.: The tao of parallelism in algorithms. In: PLDI 2011, pp. 12–25 (2011)
24.
Zurück zum Zitat Piñero, J., et al.: The DisGeNET knowledge platform for disease genomics: 2019 update. Nucl. Acids Res. 48(D1), D845–D855 (2019) Piñero, J., et al.: The DisGeNET knowledge platform for disease genomics: 2019 update. Nucl. Acids Res. 48(D1), D845–D855 (2019)
26.
Zurück zum Zitat Rogers, A., Pingali, K.: Compiling for distributed memory architectures. IEEE Trans. Parallel Distrib. Syst. 5(3), 281–298 (1994)CrossRef Rogers, A., Pingali, K.: Compiling for distributed memory architectures. IEEE Trans. Parallel Distrib. Syst. 5(3), 281–298 (1994)CrossRef
27.
Zurück zum Zitat Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.: Line. In: Proceedings of the 24th International Conference on World Wide Web (2015) Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.: Line. In: Proceedings of the 24th International Conference on World Wide Web (2015)
29.
Zurück zum Zitat Tu, K., Cui, P., Wang, X., Wang, F., Zhu, W.: Structural deep embedding for hyper-networks (2018) Tu, K., Cui, P., Wang, X., Wang, F., Zhu, W.: Structural deep embedding for hyper-networks (2018)
30.
Zurück zum Zitat Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? (2019) Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? (2019)
31.
Zurück zum Zitat Yadati, N., Nimishakavi, M., Yadav, P., Nitin, V., Louis, A., Talukdar, P.: HyperGCN: a new method of training graph convolutional networks on hypergraphs (2019) Yadati, N., Nimishakavi, M., Yadav, P., Nitin, V., Louis, A., Talukdar, P.: HyperGCN: a new method of training graph convolutional networks on hypergraphs (2019)
32.
Zurück zum Zitat Yang, J., Leskovec, J.: Defining and evaluating network communities based on ground-truth (2012) Yang, J., Leskovec, J.: Defining and evaluating network communities based on ground-truth (2012)
33.
Zurück zum Zitat Zhang, M., Cui, Z., Jiang, S., Chen, Y.: Beyond link prediction: predicting hyperlinks in adjacency space. In: AAAI, pp. 4430–4437 (2018) Zhang, M., Cui, Z., Jiang, S., Chen, Y.: Beyond link prediction: predicting hyperlinks in adjacency space. In: AAAI, pp. 4430–4437 (2018)
34.
Zurück zum Zitat Zhang, R., Zou, Y., Ma, J.: Hyper-SAGNN: a self-attention based graph neural network for hypergraphs. In: International Conference on Learning Representations (ICLR) (2020) Zhang, R., Zou, Y., Ma, J.: Hyper-SAGNN: a self-attention based graph neural network for hypergraphs. In: International Conference on Learning Representations (ICLR) (2020)
35.
Zurück zum Zitat Zheng, V.W., Cao, B., Zheng, Y., Xie, X., Yang, Q.: Collaborative filtering meets mobile recommendation: a user-centered approach. In: Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence (2010) Zheng, V.W., Cao, B., Zheng, Y., Xie, X., Yang, Q.: Collaborative filtering meets mobile recommendation: a user-centered approach. In: Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence (2010)
Metadaten
Titel
HyperNetVec: Fast and Scalable Hierarchical Embedding for Hypergraphs
verfasst von
Sepideh Maleki
Donya Saless
Dennis P. Wall
Keshav Pingali
Copyright-Jahr
2022
DOI
https://doi.org/10.1007/978-3-030-97240-0_13

Premium Partner