Abstract
Using the appropriate metric is crucial for the performance of most of machine learning algorithms. For this reason, a lot of effort has been put into distance and similarity learning. However, it is worth noting that this research field lacks theoretical guarantees that can be expected on the generalization capacity of the classifier associated to a learned metric. The theoretical framework of \((\epsilon , \gamma , \tau )\)-good similarity functions [1] provides means to relate the properties of a similarity function and those of a linear classifier making use of it. In this paper, we extend this theory to a method where the metric and the separator are jointly learned in a semi-supervised way, setting that has not been explored before. We furthermore prove the robustness of our algorithm, which allows us to provide a generalization bound for this approach. The behavior of our method is illustrated via some experimental results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Balcan, M.F., Blum, A., Srebro, N.: Improved guarantees for learning via similarity functions. In: COLT, pp. 287–298. Omnipress (2008)
Bao, J.P., Shen, J.Y., Liu, X.D., Liu, H.Y.: Quick asymmetric text similarity measures. ICMLC (2003)
Baoli, L., Qin, L., Shiwen, Y.: An adaptive k-nearest neighbor text categorization strategy. ACM TALIP 3, 215–226 (2004)
Bellet, A., Habrard, A., Sebban, M.: Similarity learning for provably accurate sparse linear classification. ICML 2012, 1871–1878 (2012)
Bellet, A., Habrard, A., Sebban, M.: A survey on metric learning for feature vectors and structured data. arXiv preprint arXiv:1306.6709 (2013)
Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: ICML, pp. 209–216. ACM, New York (2007)
Diligenti, M., Maggini, M., Rigutini, L.: Learning similarities for text documents using neural networks. In: ANNPR (2003)
Grabowski, M., Szałas, A.: A technique for learning similarities on complex structures with applications to extracting ontologies. In: Szczepaniak, P.S., Kacprzyk, J., Niewiadomski, A. (eds.) AWIC 2005. LNCS (LNAI), vol. 3528, pp. 183–189. Springer, Heidelberg (2005)
Guo, Z.C., Ying, Y.: Guaranteed classification via regularized similarity learning. CoRR abs/1306.3108 (2013)
Hoi, S.C.H., Liu, W., Chang, S.F.: Semi-supervised distance metric learning for collaborative image retrieval and clustering. TOMCCAP 6(3), 18 (2010)
Hust, A.: Learning similarities for collaborative information retrieval. In: Machine Learning and Interaction for Text-Based Information Retrieval Workshop, TIR-04, pp. 43–54 (2004)
Kolmogorov, A., Tikhomirov, V.: \(\epsilon \)-entropy and \(\epsilon \)-capacity of sets in functional spaces. Am. Math. Soc. Transl. 2(17), 277–364 (1961)
Qamar, A.M., Gaussier, É.: Online and batch learning of generalized cosine similarities. In: ICDM, pp. 926–931 (2009)
Shalev-Shwartz, S., Singer, Y., Ng, A.Y.: Online and batch learning of pseudo-metrics. In: ICML. ACM, New York (2004)
van der Vaart, A., Wellner, J.: Weak Convergence and Empirical Processes. Springer Series in Statistics. Springer, New York (1996)
Weinberger, K., Saul, L.: Distance metric learning for large margin nearest neighbor classification. JMLR 10, 207–244 (2009)
Xu, H., Mannor, S.: Robustness and generalization. In: COLT, pp. 503–515 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Nicolae, MI., Sebban, M., Habrard, A., Gaussier, E., Amini, MR. (2015). Algorithmic Robustness for Semi-Supervised \((\epsilon , \gamma , \tau )\)-Good Metric Learning. In: Arik, S., Huang, T., Lai, W., Liu, Q. (eds) Neural Information Processing. ICONIP 2015. Lecture Notes in Computer Science(), vol 9489. Springer, Cham. https://doi.org/10.1007/978-3-319-26532-2_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-26532-2_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26531-5
Online ISBN: 978-3-319-26532-2
eBook Packages: Computer ScienceComputer Science (R0)