Multiple-instance learning with pairwise instance similarity
Multiple-Instance Learning (MIL) has attracted much attention of the machine learning community in recent years and many real-world applications have been successfully formulated as MIL problems. Over the past few years, several Instance Selection-based MIL (ISMIL) algorithms have been presented by...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Sciendo
2014-09-01
|
Series: | International Journal of Applied Mathematics and Computer Science |
Subjects: | |
Online Access: | https://doi.org/10.2478/amcs-2014-0041 |
id |
doaj-3fdc14974901490380b95389a6b16f39 |
---|---|
record_format |
Article |
spelling |
doaj-3fdc14974901490380b95389a6b16f392021-09-06T19:41:08ZengSciendoInternational Journal of Applied Mathematics and Computer Science2083-84922014-09-0124356757710.2478/amcs-2014-0041amcs-2014-0041Multiple-instance learning with pairwise instance similarityYuan Liming0Liu Jiafeng1Tang Xianglong2School of Computer Science and Technology Harbin Institute of Technology, Harbin 150001, ChinaSchool of Computer Science and Technology Harbin Institute of Technology, Harbin 150001, ChinaSchool of Computer Science and Technology Harbin Institute of Technology, Harbin 150001, ChinaMultiple-Instance Learning (MIL) has attracted much attention of the machine learning community in recent years and many real-world applications have been successfully formulated as MIL problems. Over the past few years, several Instance Selection-based MIL (ISMIL) algorithms have been presented by using the concept of the embedding space. Although they delivered very promising performance, they often require long computation times for instance selection, leading to a low efficiency of the whole learning process. In this paper, we propose a simple and efficient ISMIL algorithm based on the similarity of pairwise instances within a bag. The basic idea is selecting from every training bag a pair of the most similar instances as instance prototypes and then mapping training bags into the embedding space that is constructed from all the instance prototypes. Thus, the MIL problem can be solved with the standard supervised learning techniques, such as support vector machines. Experiments show that the proposed algorithm is more efficient than its competitors and highly comparable with them in terms of classification accuracy. Moreover, the testing of noise sensitivity demonstrates that our MIL algorithm is very robust to labeling noisehttps://doi.org/10.2478/amcs-2014-0041multiple-instance learninginstance selectionsimilaritysupport vector machines |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yuan Liming Liu Jiafeng Tang Xianglong |
spellingShingle |
Yuan Liming Liu Jiafeng Tang Xianglong Multiple-instance learning with pairwise instance similarity International Journal of Applied Mathematics and Computer Science multiple-instance learning instance selection similarity support vector machines |
author_facet |
Yuan Liming Liu Jiafeng Tang Xianglong |
author_sort |
Yuan Liming |
title |
Multiple-instance learning with pairwise instance similarity |
title_short |
Multiple-instance learning with pairwise instance similarity |
title_full |
Multiple-instance learning with pairwise instance similarity |
title_fullStr |
Multiple-instance learning with pairwise instance similarity |
title_full_unstemmed |
Multiple-instance learning with pairwise instance similarity |
title_sort |
multiple-instance learning with pairwise instance similarity |
publisher |
Sciendo |
series |
International Journal of Applied Mathematics and Computer Science |
issn |
2083-8492 |
publishDate |
2014-09-01 |
description |
Multiple-Instance Learning (MIL) has attracted much attention of the machine learning community in recent years and many real-world applications have been successfully formulated as MIL problems. Over the past few years, several Instance Selection-based MIL (ISMIL) algorithms have been presented by using the concept of the embedding space. Although they delivered very promising performance, they often require long computation times for instance selection, leading to a low efficiency of the whole learning process. In this paper, we propose a simple and efficient ISMIL algorithm based on the similarity of pairwise instances within a bag. The basic idea is selecting from every training bag a pair of the most similar instances as instance prototypes and then mapping training bags into the embedding space that is constructed from all the instance prototypes. Thus, the MIL problem can be solved with the standard supervised learning techniques, such as support vector machines. Experiments show that the proposed algorithm is more efficient than its competitors and highly comparable with them in terms of classification accuracy. Moreover, the testing of noise sensitivity demonstrates that our MIL algorithm is very robust to labeling noise |
topic |
multiple-instance learning instance selection similarity support vector machines |
url |
https://doi.org/10.2478/amcs-2014-0041 |
work_keys_str_mv |
AT yuanliming multipleinstancelearningwithpairwiseinstancesimilarity AT liujiafeng multipleinstancelearningwithpairwiseinstancesimilarity AT tangxianglong multipleinstancelearningwithpairwiseinstancesimilarity |
_version_ |
1717766979108995072 |