Kernel functions based on triplet comparisons
Machine Learning
2017-10-31 v2 Data Structures and Algorithms
Machine Learning
Abstract
Given only information in the form of similarity triplets "Object A is more similar to object B than to object C" about a data set, we propose two ways of defining a kernel function on the data set. While previous approaches construct a low-dimensional Euclidean embedding of the data set that reflects the given similarity triplets, we aim at defining kernel functions that correspond to high-dimensional embeddings. These kernel functions can subsequently be used to apply any kernel method to the data set.
Keywords
Cite
@article{arxiv.1607.08456,
title = {Kernel functions based on triplet comparisons},
author = {Matthäus Kleindessner and Ulrike von Luxburg},
journal= {arXiv preprint arXiv:1607.08456},
year = {2017}
}