Optimistic semi-supervised least squares classification

Jesse H. Krijthe; Marco Loog

doi:10.1109/ICPR.2016.7899877

Optimistic semi-supervised least squares classification

Jesse H. Krijthe, Marco Loog

Department of Computer Science

4 Citations (Scopus)

Abstract

The goal of semi-supervised learning is to improve supervised classifiers by using additional unlabeled training examples. In this work we study a simple self-learning approach to semi-supervised learning applied to the least squares classifier. We show that a soft-label and a hard-label variant of self-learning can be derived by applying block coordinate descent to two related but slightly different objective functions. The resulting soft-label approach is related to an idea about dealing with missing data that dates back to the 1930s. We show that the soft-label variant typically outperforms the hard-label variant on benchmark datasets and partially explain this behaviour by studying the relative difficulty of finding good local minima for the corresponding objective functions.

Original language	English
Title of host publication	23rd International Conference on Pattern Recognition, ICPR 2016
Number of pages	6
Publisher	IEEE
Publication date	1 Jan 2016
Pages	1677-1682
ISBN (Electronic)	978-1-5090-4847-2
DOIs	https://doi.org/10.1109/ICPR.2016.7899877
Publication status	Published - 1 Jan 2016
Event	23rd International Conference on Pattern Recognition - Cancun, Mexico Duration: 4 Dec 2016 → 8 Dec 2016 Conference number: 23

Conference

Conference	23rd International Conference on Pattern Recognition
Number	23
Country/Territory	Mexico
City	Cancun
Period	04/12/2016 → 08/12/2016

Access to Document

10.1109/ICPR.2016.7899877

Cite this

@inproceedings{ab9a0b187f3d4e69bf08f6eb1e4054ae,

title = "Optimistic semi-supervised least squares classification",

abstract = "The goal of semi-supervised learning is to improve supervised classifiers by using additional unlabeled training examples. In this work we study a simple self-learning approach to semi-supervised learning applied to the least squares classifier. We show that a soft-label and a hard-label variant of self-learning can be derived by applying block coordinate descent to two related but slightly different objective functions. The resulting soft-label approach is related to an idea about dealing with missing data that dates back to the 1930s. We show that the soft-label variant typically outperforms the hard-label variant on benchmark datasets and partially explain this behaviour by studying the relative difficulty of finding good local minima for the corresponding objective functions.",

author = "Krijthe, {Jesse H.} and Marco Loog",

year = "2016",

month = jan,

day = "1",

doi = "10.1109/ICPR.2016.7899877",

language = "English",

pages = "1677--1682",

booktitle = "23rd International Conference on Pattern Recognition, ICPR 2016",

publisher = "IEEE",

note = "23rd International Conference on Pattern Recognition ; Conference date: 04-12-2016 Through 08-12-2016",

}

TY - GEN

T1 - Optimistic semi-supervised least squares classification

AU - Krijthe, Jesse H.

AU - Loog, Marco

N1 - Conference code: 23

PY - 2016/1/1

Y1 - 2016/1/1

N2 - The goal of semi-supervised learning is to improve supervised classifiers by using additional unlabeled training examples. In this work we study a simple self-learning approach to semi-supervised learning applied to the least squares classifier. We show that a soft-label and a hard-label variant of self-learning can be derived by applying block coordinate descent to two related but slightly different objective functions. The resulting soft-label approach is related to an idea about dealing with missing data that dates back to the 1930s. We show that the soft-label variant typically outperforms the hard-label variant on benchmark datasets and partially explain this behaviour by studying the relative difficulty of finding good local minima for the corresponding objective functions.

AB - The goal of semi-supervised learning is to improve supervised classifiers by using additional unlabeled training examples. In this work we study a simple self-learning approach to semi-supervised learning applied to the least squares classifier. We show that a soft-label and a hard-label variant of self-learning can be derived by applying block coordinate descent to two related but slightly different objective functions. The resulting soft-label approach is related to an idea about dealing with missing data that dates back to the 1930s. We show that the soft-label variant typically outperforms the hard-label variant on benchmark datasets and partially explain this behaviour by studying the relative difficulty of finding good local minima for the corresponding objective functions.

UR - http://www.scopus.com/inward/record.url?scp=85018623397&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2016.7899877

DO - 10.1109/ICPR.2016.7899877

M3 - Article in proceedings

AN - SCOPUS:85018623397

SP - 1677

EP - 1682

BT - 23rd International Conference on Pattern Recognition, ICPR 2016

PB - IEEE

T2 - 23rd International Conference on Pattern Recognition

Y2 - 4 December 2016 through 8 December 2016

ER -

Optimistic semi-supervised least squares classification

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this