Towards certified robustness of distance metric learning

Yang, X. , Guo, Y., Dong, M. and Xue, J.-H. (2024) Towards certified robustness of distance metric learning. IEEE Transactions on Neural Networks and Learning Systems, 35(3), pp. 3834-3844. (doi: 10.1109/TNNLS.2022.3199902) (PMID:36112549)

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 article, 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.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Yang, Dr Xiaochen
• Authors: Yang, X., Guo, Y., Dong, M., and Xue, J.-H.
• Subjects: Q Science > QA Mathematics
• College/School: College of Science and Engineering > School of Mathematics and Statistics > Statistics
• Journal Name: IEEE Transactions on Neural Networks and Learning Systems
• Publisher: IEEE
• ISSN: 2162-237X
• ISSN (Online): 2162-2388
• Published Online: 16 September 2022
• Copyright Holders: Copyright © 2022 IEEE
• First Published: First published in IEEE Transactions on Neural Networks and Learning Systems 35(3):3834-3844
• Publisher Policy: Reproduced in accordance with the copyright policy of the publisher