Advertisement

Performance Analysis of Graph-Based Methods for Exact and Approximate Similarity Search in Metric Spaces

  • Larissa Capobianco ShimomuraEmail author
  • Marcos R. Vieira
  • Daniel S. Kaster
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11223)

Abstract

Similarity searches are widely used to retrieve complex data, such as images, videos, and georeferenced data. Recently, graph-based methods have emerged as a very efficient alternative for similarity retrieval. However, to the best of our knowledge, there are no previous works with experimental analysis on a comprehensive number of graph-based methods using the same search algorithm and execution environment. In this work, we survey the main graph-based types currently employed for similarity searches and present an experimental evaluation of the most representative graphs on a common platform. We evaluate the relative performance behavior of the tested graph-based methods with respect to the main construction and query parameters for a variety of real-world datasets. Our experimental results provide a quantitative view of the exact search compared to accurate setups for approximate search. These results reinforce the tradeoff between graph construction cost and search performance according to the construction and search parameters. With respect to the approximate methods, the Navigable Small World graph (NSW) presented the highest recall rates. Nevertheless, given a recall rate, there is no winner graph for query performance.

References

  1. 1.
    Aoyama, K., Saito, K., Yamada, T., Ueda, N.: Fast similarity search in small-world networks. In: Fortunato, S., Mangioni, G., Menezes, R., Nicosia, V. (eds.) Complex Networks. Studies in Computational Intelligence, vol. 207, pp. 185–196. Springer, Berlin (2009).  https://doi.org/10.1007/978-3-642-01206-8_16CrossRefGoogle Scholar
  2. 2.
    Arya, S., Mount, D.M.: Approximate nearest neighbor queries in fixed dimensions. In: SODA, pp. 271–280 (1993)Google Scholar
  3. 3.
    Aurenhammer, F.: Voronoi diagrams - a survey of a fundamental geometric data structure. ACM Comput. Surv. 23(3), 345–405 (1991)CrossRefGoogle Scholar
  4. 4.
    Barioni, M.C.N., dos Santos Kaster, D., Razente, H.L., Traina, A.J., Júnior, C.T.: Advanced Database Query Systems. IGI Global, Hershey (2011)Google Scholar
  5. 5.
    Boytsov, L., Naidan, B.: Engineering efficient and effective non-metric space library. In: Brisaboa, N., Pedreira, O., Zezula, P. (eds.) SISAP 2013. LNCS, vol. 8199, pp. 280–293. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-41062-8_28CrossRefGoogle Scholar
  6. 6.
    Chávez, E., Navarro, G., Baeza-Yates, R., Marroquín, J.L.: Searching in metric spaces. ACM Comput. Surv. 33(3), 273–321 (2001)CrossRefGoogle Scholar
  7. 7.
    Chávez, E., Sadit Tellez, E.: Navigating k-nearest neighbor graphs to solve nearest neighbor searches. In: Martínez-Trinidad, J.F., Carrasco-Ochoa, J.A., Kittler, J. (eds.) MCPR 2010. LNCS, vol. 6256, pp. 270–280. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15992-3_29CrossRefGoogle Scholar
  8. 8.
    Dong, W., Moses, C., Li, K.: Efficient K-nearest neighbor graph construction for generic similarity measures. In: Proceedings of WWW, pp. 577–586 (2011)Google Scholar
  9. 9.
    Florez, O.U., Qi, X., Ocsa, A.: MOBHRG: fast k-nearest-neighbor search by overlap reduction of hyperspherical regions. In: ICASSP, pp. 1133–1136 (2009)Google Scholar
  10. 10.
    Hajebi, K., Abbasi-Yadkori, Y., Shahbazi, H., Zhang, H.: Fast approximate nearest-neighbor search with k-nearest neighbor graph. In: IJCAI, pp. 1312–1317 (2011)Google Scholar
  11. 11.
    Harwood, B., Drummond, T.: FANNG: fast approximate nearest neighbour graphs. In: CVPR, pp. 5713–5722 (2016)Google Scholar
  12. 12.
    Hjaltason, G.R., Samet, H.: Index-driven similarity search in metric spaces. ACM Trans. Database Syst. 28(4), 517–580 (2003)CrossRefGoogle Scholar
  13. 13.
    Iwasaki, M.: Pruned bi-directed k-nearest neighbor graph for proximity search. In: Amsaleg, L., Houle, M.E., Schubert, E. (eds.) SISAP 2016. LNCS, vol. 9939, pp. 20–33. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46759-7_2CrossRefGoogle Scholar
  14. 14.
    Jaromczyk, J.W., Toussaint, G.T.: Relative neighborhood graphs and their relatives. Proc. IEEE 80(9), 1502–1517 (1992)CrossRefGoogle Scholar
  15. 15.
    Jegou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. PAMI 33(1), 117–128 (2011)CrossRefGoogle Scholar
  16. 16.
    Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  17. 17.
    Malkov, Y., Ponomarenko, A., Logvinov, A., Krylov, V.: Scalable distributed algorithm for approximate nearest neighbor search problem in high dimensional general metric spaces. In: Navarro, G., Pestov, V. (eds.) SISAP 2012. LNCS, vol. 7404, pp. 132–147. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-32153-5_10CrossRefGoogle Scholar
  18. 18.
    Malkov, Y., et al.: Approximate nearest neighbor algorithm based on navigable small world graphs. Inf. Syst. 45, 61–68 (2014)CrossRefGoogle Scholar
  19. 19.
    Naidan, B., Boytsov, L., Nyberg, E.: Permutation search methods are efficient, yet faster search is possible. Proc. VLDB Endow. 8(12), 1618–1629 (2015)CrossRefGoogle Scholar
  20. 20.
    Navarro, G.: Searching in metric spaces by spatial approximation. VLDB J. 11(1), 28–46 (2002)CrossRefGoogle Scholar
  21. 21.
    Ocsa, A., Bedregal, C., Cuadros-Vargas, E.: A new approach for similarity queries using neighborhood graphs. In: Brazilian Symposium on Databases, pp. 131–142 (2007)Google Scholar
  22. 22.
    Ortega, M., Rui, Y., Chakrabarti, K., Porkaew, K., Mehrotra, S., Huang, T.S.: Supporting ranked Boolean similarity queries in MARS. TKDE 10(6), 905–925 (1998)Google Scholar
  23. 23.
    Paredes, R., Chávez, E.: Using the k-nearest neighbor graph for proximity searching in metric spaces. In: Consens, M., Navarro, G. (eds.) SPIRE 2005. LNCS, vol. 3772, pp. 127–138. Springer, Heidelberg (2005).  https://doi.org/10.1007/11575832_14CrossRefGoogle Scholar
  24. 24.
    Paredes, R., Chávez, E., Figueroa, K., Navarro, G.: Practical construction of k-nearest neighbor graphs in metric spaces. In: Àlvarez, C., Serna, M. (eds.) WEA 2006. LNCS, vol. 4007, pp. 85–97. Springer, Heidelberg (2006).  https://doi.org/10.1007/11764298_8CrossRefGoogle Scholar
  25. 25.
    Skopal, T., Bustos, B.: On nonmetric similarity search problems in complex domains. ACM Comput. Surv. 43(4), 1–50 (2011)CrossRefGoogle Scholar
  26. 26.
    Wang, J., Li, S.: Query-driven iterated neighborhood graph search for large scale indexing. In: ACM MM, pp. 179–188 (2012)Google Scholar
  27. 27.
    Wang, J., Wang, J., Zeng, G., Tu, Z., Gan, R., Li, S.: Scalable k-NN graph construction for visual descriptors. In: CVPR, pp. 1106–1113 (2012)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Larissa Capobianco Shimomura
    • 1
    Email author
  • Marcos R. Vieira
    • 2
  • Daniel S. Kaster
    • 1
  1. 1.University of LondrinaLondrinaBrazil
  2. 2.Hitachi America Ltd, R&DSanta ClaraUSA

Personalised recommendations