Learning relative similarity from data streams: Active online learning approaches

Relative similarity learning, as an important learning scheme for information retrieval, aims to learn a bi-linear similarity function from a collection of labeled instance-pairs, and the learned function would assign a high similarity value for a similar instance-pair and a low value for a dissimil...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuji Hao, Peilin Zhao, HOI, Steven C. H., Chunyan Miao
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2015
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/2925
https://ink.library.smu.edu.sg/context/sis_research/article/3925/viewcontent/LearningRelativeSimilarityDataStreams_CIKM_2015_afv.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-3925
record_format dspace
spelling sg-smu-ink.sis_research-39252017-01-09T15:24:06Z Learning relative similarity from data streams: Active online learning approaches Shuji Hao, Peilin Zhao, HOI, Steven C. H. Chunyan Miao, Relative similarity learning, as an important learning scheme for information retrieval, aims to learn a bi-linear similarity function from a collection of labeled instance-pairs, and the learned function would assign a high similarity value for a similar instance-pair and a low value for a dissimilar pair. Existing algorithms usually assume the labels of all the pairs in data streams are always made available for learning. However, this is not always realistic in practice since the number of possible pairs is quadratic to the number of instances in the database, and manually labeling the pairs could be very costly and time consuming. To overcome the limitation, we propose a novel framework of active online similarity learning. Specifically, we propose two new algorithms: (i)~PAAS: Passive-Aggressive Active Similarity learning; (ii)~CWAS: Confidence-Weighted Active Similarity learning, and we will prove their mistake bounds in theory. We have conducted extensive experiments on a variety of real-world data sets, and we find encouraging results that validate the empirical effectiveness of the proposed algorithms. 2015-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/2925 info:doi/10.1145/2806416.2806464 https://ink.library.smu.edu.sg/context/sis_research/article/3925/viewcontent/LearningRelativeSimilarityDataStreams_CIKM_2015_afv.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University machine learning data streams online learning Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic machine learning
data streams
online learning
Databases and Information Systems
spellingShingle machine learning
data streams
online learning
Databases and Information Systems
Shuji Hao,
Peilin Zhao,
HOI, Steven C. H.
Chunyan Miao,
Learning relative similarity from data streams: Active online learning approaches
description Relative similarity learning, as an important learning scheme for information retrieval, aims to learn a bi-linear similarity function from a collection of labeled instance-pairs, and the learned function would assign a high similarity value for a similar instance-pair and a low value for a dissimilar pair. Existing algorithms usually assume the labels of all the pairs in data streams are always made available for learning. However, this is not always realistic in practice since the number of possible pairs is quadratic to the number of instances in the database, and manually labeling the pairs could be very costly and time consuming. To overcome the limitation, we propose a novel framework of active online similarity learning. Specifically, we propose two new algorithms: (i)~PAAS: Passive-Aggressive Active Similarity learning; (ii)~CWAS: Confidence-Weighted Active Similarity learning, and we will prove their mistake bounds in theory. We have conducted extensive experiments on a variety of real-world data sets, and we find encouraging results that validate the empirical effectiveness of the proposed algorithms.
format text
author Shuji Hao,
Peilin Zhao,
HOI, Steven C. H.
Chunyan Miao,
author_facet Shuji Hao,
Peilin Zhao,
HOI, Steven C. H.
Chunyan Miao,
author_sort Shuji Hao,
title Learning relative similarity from data streams: Active online learning approaches
title_short Learning relative similarity from data streams: Active online learning approaches
title_full Learning relative similarity from data streams: Active online learning approaches
title_fullStr Learning relative similarity from data streams: Active online learning approaches
title_full_unstemmed Learning relative similarity from data streams: Active online learning approaches
title_sort learning relative similarity from data streams: active online learning approaches
publisher Institutional Knowledge at Singapore Management University
publishDate 2015
url https://ink.library.smu.edu.sg/sis_research/2925
https://ink.library.smu.edu.sg/context/sis_research/article/3925/viewcontent/LearningRelativeSimilarityDataStreams_CIKM_2015_afv.pdf
_version_ 1770572739893002240