# Towards Self-Adaptive Metric Learning On the Fly

arXiv: https://arxiv.org/abs/2104.01495 · HTML: https://mlsanity.com/paper/2104.01495/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 3 Apr 2021.

## Builds on (most cited first, 10 of 10)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Net2Net: Accelerating Learning via Knowledge Transfer](https://mlsanity.com/paper/1511.05641/) (2015)
- [EMNIST: an extension of MNIST to handwritten letters](https://mlsanity.com/paper/1702.05373/) (2017)
- [Online Deep Learning: Learning Deep Neural Networks on the Fly](https://mlsanity.com/paper/1711.03705/) (2017)
- [A Survey on Metric Learning for Feature Vectors and Structured Data](https://mlsanity.com/paper/1306.6709/) (2013)
- [Mollifying Networks](https://mlsanity.com/paper/1608.04980/) (2016)
- [Learning Neural Network Architectures using Backpropagation](https://mlsanity.com/paper/1511.05497/) (2015)
- [OPML: A One-Pass Closed-Form Solution for Online Metric Learning](https://mlsanity.com/paper/1609.09178/) (2016)

## Built on by (most cited first, 2 of 2)

- [An Automated Vulnerability Detection Framework for Smart Contracts](https://mlsanity.com/paper/2301.08824/) (2023)
- [Vulnerability Detection in Ethereum Smart Contracts via Machine Learning: A Qualitative Analysis](https://mlsanity.com/paper/2407.18639/) (2024)

## Abstract (arXiv)

Good quality similarity metrics can significantly facilitate the performance of many large-scale, real-world applications. Existing studies have proposed various solutions to learn a Mahalanobis or bilinear metric in an online fashion by either restricting distances between similar (dissimilar) pairs to be smaller (larger) than a given lower (upper) bound or requiring similar instances to be separated from dissimilar instances with a given margin. However, these linear metrics learned by leveraging fixed bounds or margins may not perform well in real-world applications, especially when data distributions are complex. We aim to address the open challenge of "Online Adaptive Metric Learning" (OAML) for learning adaptive metric functions on the fly. Unlike traditional online metric learning methods, OAML is significantly more challenging since the learned metric could be non-linear and the model has to be self-adaptive as more instances are observed. In this paper, we present a new online metric learning framework that attempts to tackle the challenge by learning an ANN-based metric with adaptive model complexity from a stream of constraints. In particular, we propose a novel Adaptive-Bound Triplet Loss (ABTL) to effectively utilize the input constraints and present a novel Adaptive Hedge Update (AHU) method for online updating the model parameters. We empirically validate the effectiveness and efficacy of our framework on various applications such as real-world image classification, facial verification, and image retrieval.