Skip to main content

Robust Cardinality Estimator by Non-autoregressive Model

  • 67 Accesses

Part of the Communications in Computer and Information Science book series (CCIS,volume 1457)

Abstract

In database systems, cardinality estimation is a fundamental technology that significantly impacts query performance. Recently, machine-learning techniques are employed for cardinality estimation, which learns dependencies among attributes. However, they have a problem that the estimation accuracy is unstable and the inference speed is slow. In this paper, we propose a stable and fast cardinality estimation method that learns dependencies among attributes by a non-autoregressive model and performs estimation in fewer steps and proper order according to a given query at the inference phase.

Keywords

  • Cardinality estimation
  • Machine learning

This paper is based on results obtained from a project, JPNP16007, commissioned by the New Energy and Industrial Technology Development Organization (NEDO).

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-93849-9_3
  • Chapter length: 7 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   59.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-93849-9
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   74.99
Price excludes VAT (USA)

Notes

  1. 1.

    Any non-autoregressive model (e.g., Transformer-based model) can be used.

  2. 2.

    Only the decoder.

References

  1. Chow, C., Liu, C.: Approximating discrete probability distributions with dependence trees. IEEE Trans. Inf. Theory 14(3), 462–467 (1968)

    CrossRef  Google Scholar 

  2. Germain, M., Gregor, K., Murray, I., Larochelle, H.: MADE: masked autoencoder for distribution estimation. In: PMLR (2015)

    Google Scholar 

  3. Hilprecht, B., Schmidt, A., Kulessa, M., Molina, A., Kersting, K., Binnig, C.: DeepDB: Learn from Data, not from Queries! VLDB (2019)

    Google Scholar 

  4. Kipf, A., Kipf, T., Radke, B., Leis, V., Boncz, P., Kemper, A.: Learned cardinalities: estimating correlated joins with deep learning. In: CIDR (2019)

    Google Scholar 

  5. Leis, V., Gubichev, A., Mirchev, A., Boncz, P., Kemper, A., Neumann, T.: How good are query optimizers, really? VLDB 9(3), 204–215 (2015)

    Google Scholar 

  6. Poon, H., Domingos, P.: Sum-product networks: a new deep architecture. In: AAAI (2017)

    Google Scholar 

  7. Poosala, V., Ioannidis, Y.E., Haas, P.J., Shekita, E.J.: Improved histograms for selectivity estimation of range predicates. In: ICDE (1996)

    Google Scholar 

  8. State of New York: Vehicle, Snowmobile, and Boat Registrations. https://catalog.data.gov/dataset/vehicle-snowmobile-and-boat-registrations (2019)

  9. Vaswani, A., et al.: Attention Is All You Need. In: NIPS (2017)

    Google Scholar 

  10. Yang, Z., et al.: NeuroCard: One Cardinality Estimator for All Tables. VLDB (2021)

    Google Scholar 

  11. Yang, Z., et al.: Deep Unsupervised Cardinality Estimation. VLDB (2019)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ryuichi Ito .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2022 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Ito, R., Xiao, C., Onizuka, M. (2022). Robust Cardinality Estimator by Non-autoregressive Model. In: Fletcher, G., Nakano, K., Sasaki, Y. (eds) Software Foundations for Data Interoperability. SFDI 2021. Communications in Computer and Information Science, vol 1457. Springer, Cham. https://doi.org/10.1007/978-3-030-93849-9_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-93849-9_3

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-93848-2

  • Online ISBN: 978-3-030-93849-9

  • eBook Packages: Computer ScienceComputer Science (R0)