UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Toward Certified Robustness of Distance Metric Learning

Yang, Xiaochen; Guo, Yiwen; Dong, Mingzhi; Xue, Jing-Hao; (2022) Toward Certified Robustness of Distance Metric Learning. IEEE Transactions on Neural Networks and Learning Systems pp. 1-11. 10.1109/tnnls.2022.3199902. (In press). Green open access

[thumbnail of Xue_Toward Certified Robustness of Distance Metric Learning_AAM2.pdf]
Preview
Text
Xue_Toward Certified Robustness of Distance Metric Learning_AAM2.pdf

Download (2MB) | Preview

Abstract

Metric learning aims to learn a distance metric such that semantically similar instances are pulled together while dissimilar instances are pushed away. Many existing methods consider maximizing or at least constraining a distance margin in the feature space that separates similar and dissimilar pairs of instances to guarantee their generalization ability. In this paper, we advocate imposing an adversarial margin in the input space so as to improve the generalization and robustness of metric learning algorithms. We first show that, the adversarial margin, defined as the distance between training instances and their closest adversarial examples in the input space, takes account of both the distance margin in the feature space and the correlation between the metric and triplet constraints. Next, to enhance robustness to instance perturbation, we propose to enlarge the adversarial margin through minimizing a derived novel loss function termed the perturbation loss. The proposed loss can be viewed as a data-dependent regularizer and easily plugged into any existing metric learning methods. Finally, we show that the enlarged margin is beneficial to the generalization ability by using the theoretical technique of algorithmic robustness. Experimental results on 16 datasets demonstrate the superiority of the proposed method over existing state-of-the-art methods in both discrimination accuracy and robustness against possible noise.

Type: Article
Title: Toward Certified Robustness of Distance Metric Learning
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/tnnls.2022.3199902
Publisher version: https://doi.org/10.1109/TNNLS.2022.3199902
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
Keywords: Adversarial perturbation, generalization ability, 26 metric learning, nearest neighbor (NN), robustness
UCL classification: UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL
URI: https://discovery.ucl.ac.uk/id/eprint/10155883
Downloads since deposit
89Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item