A Bayesian approach to abrupt concept drift

被引：5

作者：

Cano, Andres ^{[1
]}

Gomez-Olmedo, Manuel ^{[1
]}

Moral, Serafin ^{[1
]}

机构：

[1] Univ Granada, Dept Ciencias Comp & IA, E-18071 Granada, Spain

来源：

KNOWLEDGE-BASED SYSTEMS | 2019年 / 185卷

关键词：

Concept drift; Dynamic Bayesian networks; Change detection; Propagation algorithms; CLASSIFIERS;

D O I：

10.1016/j.knosys.2019.104909

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper proposes a model for estimating probabilities in the presence of abrupt concept drift. This proposal is based on a dynamic Bayesian network. As the exact estimation of the parameters is unfeasible we propose an approximate procedure based on discretizing both the possible probability values and the parameter representing the probability of change. The result is a method which is quite efficient in time and space (with a complexity directly related to the number of points used in the discretization) and providing very accurate predictions as well. These benefits are checked with a detailed comparison with other standard procedures based on variable size windows or forgetting rates. (C) 2019 Elsevier B.V. All rights reserved.

引用

页数：14

共 30 条

[1]

Abellan J., 2006, Proc. 3rd Eur. Workshop Probabilistic Graphical Models, Prague, P1

[2]

[Anonymous], 2000, P ECAI 2000 WORKSH C

[3]

[Anonymous], 2004, VLDB

[4]

Babcock Brian, 2002, PODS, P1, DOI DOI 10.1145/543613.543615

[5]

Bifet A, 2007, PROCEEDINGS OF THE SEVENTH SIAM INTERNATIONAL CONFERENCE ON DATA MINING, P443

[6] Virtual Subconcept Drift Detection in Discrete Data Using Probabilistic Graphical Models [J].

Cabanas, Rafael ;

Cano, Andres ;

Gomez-Olmedo, Manuel ;

Masegosa, Andres R. ;

Moral, Serafin .

INFORMATION PROCESSING AND MANAGEMENT OF UNCERTAINTY IN KNOWLEDGE-BASED SYSTEMS: APPLICATIONS, IPMU 2018, PT III, 2018, 855 :616-628

[7]

Chakraborty S., 2015, Journal of Statistical Distributions and Applications, V2, P1, DOI DOI 10.1186/S40488-015-0028-6

[8] Maintaining stream statistics over sliding windows [J].

Datar, M ;

Gionis, A ;

Indyk, P ;

Motwani, R .

SIAM JOURNAL ON COMPUTING, 2002, 31 (06) :1794-1813

[9]

Demsar J, 2006, J MACH LEARN RES, V7, P1

[10] Improving the precision of estimates of the frequency of rare events [J].

Dixon, PM ;

Ellison, AM ;

Gotelli, NJ .

ECOLOGY, 2005, 86 (05) :1114-1123

← 1 2 3 →