Learning Embeddings from Probabilistic Triplet Comparisons

No Thumbnail Available

URL

Journal Title

Journal ISSN

Volume Title

Perustieteiden korkeakoulu | Master's thesis

Date

2018-10-08

Department

Major/Subject

Networking Technology

Mcode

ELEC3029

Degree programme

Master’s Programme in Computer, Communication and Information Sciences

Language

en

Pages

79+2

Series

Abstract

Learning from relative similarity comparisons has gained interest in the data science community in the past 20 years. We introduce a new way to capture relative similarity comparisons called probabilistic triplets that alleviates extreme decisions under high uncertainty, and provides finer-grained information than ordinary triplets. We describe a new method called t-SPTE that finds an embedding of objects in a Euclidean space using probabilistic triplets datasets as its input. The problem is formulated as a least squares optimization of differences between the labeled triplet probabilities and the triplet probabilities coming from the stochastic neighborhood model in the embedding space. We experimentally show that our approach improves upon previous methods, notably t-STE, needing less labeled triplets and producing higher quality embeddings.

Description

Supervisor

Gionis, Aristides

Thesis advisor

Ukkonen, Antti

Keywords

embeddings, representation learning, ordinal constraints, relative similarity comparisons, probabilistic triplets, certainty

Other note

Citation