Active Metric Learning And Classification Using Similarity Queries

Abstract

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 informatio

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynadagouda2022active

Related papers

• Similarity Function Tracking Using Pairwise Comparisons (2017)2.26
• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Metric Learning By Similarity Network For Deep Semi-supervised Learning (2020)3.58
• Discriminative Learning Of Similarity And Group Equivariant Representations (2018)0.00
• Large Scale Local Online Similarity/distance Learning Framework Based On Passive/aggressive (2018)2.26
• Dynamic Metric Learning From Pairwise Comparisons (2016)3.58
• Sparse Online Relative Similarity Learning (2021)2.26
• Active Nearest-neighbor Learning In Metric Spaces (2016)0.00