# Active metric learning and classification using similarity queries

arXiv: https://arxiv.org/abs/2202.01953 · HTML: https://mlsanity.com/paper/2202.01953/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 52 references that are in the map.
- First posted on arXiv 4 Feb 2022.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Beyond triplet loss: a deep quadruplet network for person re-identification](https://mlsanity.com/paper/1704.01719/) (2017)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost](https://mlsanity.com/paper/1910.07153/) (2019)
- [Deep Metric Learning with Hierarchical Triplet Loss](https://mlsanity.com/paper/1810.06951/) (2018)
- [Bayesian Batch Active Learning as Sparse Subset Approximation](https://mlsanity.com/paper/1908.02144/) (2019)
- [Learning Type-Aware Embeddings for Fashion Compatibility](https://mlsanity.com/paper/1803.09196/) (2018)
- [Combining MixMatch and Active Learning for Better Accuracy with Fewer Labels](https://mlsanity.com/paper/1912.00594/) (2019)
- [Bayesian representation learning with oracle constraints](https://mlsanity.com/paper/1506.05011/) (2015)
- [Cost-Effective HITs for Relative Similarity Comparisons](https://mlsanity.com/paper/1404.3291/) (2014)
- [Triplet Probabilistic Embedding for Face Verification and Clustering](https://mlsanity.com/paper/1604.05417/) (2016)
- [Predicting Choice with Set-Dependent Aggregation](https://mlsanity.com/paper/1906.06365/) (2019)
- [Active embedding search via noisy paired comparisons](https://mlsanity.com/paper/1905.04363/) (2019)
- [Active Ordinal Querying for Tuplewise Similarity Learning](https://mlsanity.com/paper/1910.04115/) (2019)
- [Landmark Ordinal Embedding](https://mlsanity.com/paper/1910.12379/) (2019)
- [Robust Ordinal Embedding from Contaminated Relative Comparisons](https://mlsanity.com/paper/1812.01945/) (2018)
- [Active Perceptual Similarity Modeling with Auxiliary Information](https://mlsanity.com/paper/1511.02254/) (2015)
- [Uncertainty Estimates for Ordinal Embeddings](https://mlsanity.com/paper/1906.11655/) (2019)
- [Batch Decorrelation for Active Metric Learning](https://mlsanity.com/paper/2005.10008/) (2020)

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

- [Active Learning of Ordinal Embeddings: A User Study on Football Data](https://mlsanity.com/paper/2207.12710/) (2022)
- [Metric Learning in an RKHS](https://mlsanity.com/paper/2508.04476/) (2025)

## Abstract (arXiv)

Active learning is commonly used to train label-efficient models by adaptively selecting the most informative queries. However, most active learning strategies are designed to either learn a representation of the data (e.g., embedding or metric learning) or perform well on a task (e.g., classification) on the data. However, many machine learning tasks involve a combination of both representation learning and a task-specific goal. Motivated by this, we propose a novel unified query framework that can be applied to any problem in which a key component is learning a representation of the data that reflects similarity. Our approach builds on similarity or nearest neighbor (NN) queries which seek to select samples that result in improved embeddings. The queries consist of a reference and a set of objects, with an oracle selecting the object most similar (i.e., nearest) to the reference. In order to reduce the number of solicited queries, they are chosen adaptively according to an information theoretic criterion. We demonstrate the effectiveness of the proposed strategy on two tasks -- active metric learning and active classification -- using a variety of synthetic and real world datasets. In particular, we demonstrate that actively selected NN queries outperform recently developed active triplet selection methods in a deep metric learning setting. Further, we show that in classification, actively selecting class labels can be reformulated as a process of selecting the most informative NN query, allowing direct application of our method.