Adaptive Learning from Evolving Data Streams. Bifet, A. & Gavaldà, R. In Adams, N. M., Robardet, C., Siebes, A., & Boulicaut, J., editors, Advances in Intelligent Data Analysis VIII, pages 249–260, Berlin, Heidelberg, 2009. Springer. doi abstract bibtex We propose and illustrate a method for developing algorithms that can adaptively learn from data streams that drift over time. As an example, we take Hoeffding Tree, an incremental decision tree inducer for data streams, and use as a basis it to build two new methods that can deal with distribution and concept drift: a sliding window-based algorithm, Hoeffding Window Tree, and an adaptive method, Hoeffding Adaptive Tree. Our methods are based on using change detectors and estimator modules at the right places; we choose implementations with theoretical guarantees in order to extend such guarantees to the resulting adaptive learning algorithm. A main advantage of our methods is that they require no guess about how fast or how often the stream will drift; other methods typically have several user-defined parameters to this effect.
@inproceedings{bifet_adaptive_2009,
address = {Berlin, Heidelberg},
title = {Adaptive {Learning} from {Evolving} {Data} {Streams}},
isbn = {978-3-642-03915-7},
doi = {10.1007/978-3-642-03915-7_22},
abstract = {We propose and illustrate a method for developing algorithms that can adaptively learn from data streams that drift over time. As an example, we take Hoeffding Tree, an incremental decision tree inducer for data streams, and use as a basis it to build two new methods that can deal with distribution and concept drift: a sliding window-based algorithm, Hoeffding Window Tree, and an adaptive method, Hoeffding Adaptive Tree. Our methods are based on using change detectors and estimator modules at the right places; we choose implementations with theoretical guarantees in order to extend such guarantees to the resulting adaptive learning algorithm. A main advantage of our methods is that they require no guess about how fast or how often the stream will drift; other methods typically have several user-defined parameters to this effect.},
language = {en},
booktitle = {Advances in {Intelligent} {Data} {Analysis} {VIII}},
publisher = {Springer},
author = {Bifet, Albert and Gavaldà, Ricard},
editor = {Adams, Niall M. and Robardet, Céline and Siebes, Arno and Boulicaut, Jean-François},
year = {2009},
pages = {249--260},
}
Downloads: 0
{"_id":"EcbL2S2oSakhSNW6f","bibbaseid":"bifet-gavald-adaptivelearningfromevolvingdatastreams-2009","authorIDs":[],"author_short":["Bifet, A.","Gavaldà, R."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Berlin, Heidelberg","title":"Adaptive Learning from Evolving Data Streams","isbn":"978-3-642-03915-7","doi":"10.1007/978-3-642-03915-7_22","abstract":"We propose and illustrate a method for developing algorithms that can adaptively learn from data streams that drift over time. As an example, we take Hoeffding Tree, an incremental decision tree inducer for data streams, and use as a basis it to build two new methods that can deal with distribution and concept drift: a sliding window-based algorithm, Hoeffding Window Tree, and an adaptive method, Hoeffding Adaptive Tree. Our methods are based on using change detectors and estimator modules at the right places; we choose implementations with theoretical guarantees in order to extend such guarantees to the resulting adaptive learning algorithm. A main advantage of our methods is that they require no guess about how fast or how often the stream will drift; other methods typically have several user-defined parameters to this effect.","language":"en","booktitle":"Advances in Intelligent Data Analysis VIII","publisher":"Springer","author":[{"propositions":[],"lastnames":["Bifet"],"firstnames":["Albert"],"suffixes":[]},{"propositions":[],"lastnames":["Gavaldà"],"firstnames":["Ricard"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Adams"],"firstnames":["Niall","M."],"suffixes":[]},{"propositions":[],"lastnames":["Robardet"],"firstnames":["Céline"],"suffixes":[]},{"propositions":[],"lastnames":["Siebes"],"firstnames":["Arno"],"suffixes":[]},{"propositions":[],"lastnames":["Boulicaut"],"firstnames":["Jean-François"],"suffixes":[]}],"year":"2009","pages":"249–260","bibtex":"@inproceedings{bifet_adaptive_2009,\n\taddress = {Berlin, Heidelberg},\n\ttitle = {Adaptive {Learning} from {Evolving} {Data} {Streams}},\n\tisbn = {978-3-642-03915-7},\n\tdoi = {10.1007/978-3-642-03915-7_22},\n\tabstract = {We propose and illustrate a method for developing algorithms that can adaptively learn from data streams that drift over time. As an example, we take Hoeffding Tree, an incremental decision tree inducer for data streams, and use as a basis it to build two new methods that can deal with distribution and concept drift: a sliding window-based algorithm, Hoeffding Window Tree, and an adaptive method, Hoeffding Adaptive Tree. Our methods are based on using change detectors and estimator modules at the right places; we choose implementations with theoretical guarantees in order to extend such guarantees to the resulting adaptive learning algorithm. A main advantage of our methods is that they require no guess about how fast or how often the stream will drift; other methods typically have several user-defined parameters to this effect.},\n\tlanguage = {en},\n\tbooktitle = {Advances in {Intelligent} {Data} {Analysis} {VIII}},\n\tpublisher = {Springer},\n\tauthor = {Bifet, Albert and Gavaldà, Ricard},\n\teditor = {Adams, Niall M. and Robardet, Céline and Siebes, Arno and Boulicaut, Jean-François},\n\tyear = {2009},\n\tpages = {249--260},\n}\n\n","author_short":["Bifet, A.","Gavaldà, R."],"editor_short":["Adams, N. M.","Robardet, C.","Siebes, A.","Boulicaut, J."],"key":"bifet_adaptive_2009","id":"bifet_adaptive_2009","bibbaseid":"bifet-gavald-adaptivelearningfromevolvingdatastreams-2009","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/mh_lenguyen","creationDate":"2019-12-06T04:09:42.140Z","downloads":0,"keywords":[],"search_terms":["adaptive","learning","evolving","data","streams","bifet","gavaldà"],"title":"Adaptive Learning from Evolving Data Streams","year":2009,"dataSources":["fSK4Xnb68KncfLSNv","iwKepCrWBps7ojhDx"]}