Dealing with concept drift and class imbalance in multi-label stream classification. Xioufis, E. S., Spiliopoulou, M., Tsoumakas, G., & Vlahavas, I. In Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two, of IJCAI'11, pages 1583–1588, Barcelona, Catalonia, Spain, July, 2011. AAAI Press. abstract bibtex Streams of objects that are associated with one or more labels at the same time appear in many applications. However, stream classification of multi-label data is largely unexplored. Existing approaches try to tackle the problem by transferring traditional single-label stream classification practices to the multi-label domain. Nevertheless, they fail to consider some of the unique properties of the problem such as within and between class imbalance and multiple concept drift. To deal with these challenges, this paper proposes a novel multilabel stream classification approach that employs two windows for each label, one for positive and one for negative examples. Instance-sharing is exploited for space efficiency, while a time-efficient instantiation based on the k-Nearest Neighbor algorithm is also proposed. Finally, a batch-incremental thresholding technique is proposed to further deal with the class imbalance problem. Results of an empirical comparison against two other methods on three real world datasets are in favor of the proposed approach.
@inproceedings{xioufis_dealing_2011,
address = {Barcelona, Catalonia, Spain},
series = {{IJCAI}'11},
title = {Dealing with concept drift and class imbalance in multi-label stream classification},
isbn = {978-1-57735-514-4},
abstract = {Streams of objects that are associated with one or more labels at the same time appear in many applications. However, stream classification of multi-label data is largely unexplored. Existing approaches try to tackle the problem by transferring traditional single-label stream classification practices to the multi-label domain. Nevertheless, they fail to consider some of the unique properties of the problem such as within and between class imbalance and multiple concept drift. To deal with these challenges, this paper proposes a novel multilabel stream classification approach that employs two windows for each label, one for positive and one for negative examples. Instance-sharing is exploited for space efficiency, while a time-efficient instantiation based on the k-Nearest Neighbor algorithm is also proposed. Finally, a batch-incremental thresholding technique is proposed to further deal with the class imbalance problem. Results of an empirical comparison against two other methods on three real world datasets are in favor of the proposed approach.},
urldate = {2022-03-17},
booktitle = {Proceedings of the {Twenty}-{Second} international joint conference on {Artificial} {Intelligence} - {Volume} {Volume} {Two}},
publisher = {AAAI Press},
author = {Xioufis, Eleftherios Spyromitros and Spiliopoulou, Myra and Tsoumakas, Grigorios and Vlahavas, Ioannis},
month = jul,
year = {2011},
pages = {1583--1588},
}
Downloads: 0
{"_id":"EgcbihdyHX6BaNtTL","bibbaseid":"xioufis-spiliopoulou-tsoumakas-vlahavas-dealingwithconceptdriftandclassimbalanceinmultilabelstreamclassification-2011","author_short":["Xioufis, E. S.","Spiliopoulou, M.","Tsoumakas, G.","Vlahavas, I."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Barcelona, Catalonia, Spain","series":"IJCAI'11","title":"Dealing with concept drift and class imbalance in multi-label stream classification","isbn":"978-1-57735-514-4","abstract":"Streams of objects that are associated with one or more labels at the same time appear in many applications. However, stream classification of multi-label data is largely unexplored. Existing approaches try to tackle the problem by transferring traditional single-label stream classification practices to the multi-label domain. Nevertheless, they fail to consider some of the unique properties of the problem such as within and between class imbalance and multiple concept drift. To deal with these challenges, this paper proposes a novel multilabel stream classification approach that employs two windows for each label, one for positive and one for negative examples. Instance-sharing is exploited for space efficiency, while a time-efficient instantiation based on the k-Nearest Neighbor algorithm is also proposed. Finally, a batch-incremental thresholding technique is proposed to further deal with the class imbalance problem. Results of an empirical comparison against two other methods on three real world datasets are in favor of the proposed approach.","urldate":"2022-03-17","booktitle":"Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two","publisher":"AAAI Press","author":[{"propositions":[],"lastnames":["Xioufis"],"firstnames":["Eleftherios","Spyromitros"],"suffixes":[]},{"propositions":[],"lastnames":["Spiliopoulou"],"firstnames":["Myra"],"suffixes":[]},{"propositions":[],"lastnames":["Tsoumakas"],"firstnames":["Grigorios"],"suffixes":[]},{"propositions":[],"lastnames":["Vlahavas"],"firstnames":["Ioannis"],"suffixes":[]}],"month":"July","year":"2011","pages":"1583–1588","bibtex":"@inproceedings{xioufis_dealing_2011,\n\taddress = {Barcelona, Catalonia, Spain},\n\tseries = {{IJCAI}'11},\n\ttitle = {Dealing with concept drift and class imbalance in multi-label stream classification},\n\tisbn = {978-1-57735-514-4},\n\tabstract = {Streams of objects that are associated with one or more labels at the same time appear in many applications. However, stream classification of multi-label data is largely unexplored. Existing approaches try to tackle the problem by transferring traditional single-label stream classification practices to the multi-label domain. Nevertheless, they fail to consider some of the unique properties of the problem such as within and between class imbalance and multiple concept drift. To deal with these challenges, this paper proposes a novel multilabel stream classification approach that employs two windows for each label, one for positive and one for negative examples. Instance-sharing is exploited for space efficiency, while a time-efficient instantiation based on the k-Nearest Neighbor algorithm is also proposed. Finally, a batch-incremental thresholding technique is proposed to further deal with the class imbalance problem. Results of an empirical comparison against two other methods on three real world datasets are in favor of the proposed approach.},\n\turldate = {2022-03-17},\n\tbooktitle = {Proceedings of the {Twenty}-{Second} international joint conference on {Artificial} {Intelligence} - {Volume} {Volume} {Two}},\n\tpublisher = {AAAI Press},\n\tauthor = {Xioufis, Eleftherios Spyromitros and Spiliopoulou, Myra and Tsoumakas, Grigorios and Vlahavas, Ioannis},\n\tmonth = jul,\n\tyear = {2011},\n\tpages = {1583--1588},\n}\n\n\n\n","author_short":["Xioufis, E. S.","Spiliopoulou, M.","Tsoumakas, G.","Vlahavas, I."],"key":"xioufis_dealing_2011","id":"xioufis_dealing_2011","bibbaseid":"xioufis-spiliopoulou-tsoumakas-vlahavas-dealingwithconceptdriftandclassimbalanceinmultilabelstreamclassification-2011","role":"author","urls":{},"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":[],"search_terms":["dealing","concept","drift","class","imbalance","multi","label","stream","classification","xioufis","spiliopoulou","tsoumakas","vlahavas"],"title":"Dealing with concept drift and class imbalance in multi-label stream classification","year":2011}