A meta-learning method for concept drift

Wang, Runxin and Shi, Lei and Foghlú, Mícheál Ó and Robson, Eric (2010) A meta-learning method for concept drift. In: KDIR 2010 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval :. KDIR 2010 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval . UNSPECIFIED, ESP, pp. 257-262. ISBN 9789898425287

Full text not available from this repository. (Request a copy)

Abstract

The knowledge hidden in evolving data may change with time, this issue is known as concept drift. It often causes a learning system to decrease its prediction accuracy. Most existing techniques apply ensemble methods to improve learning performance on concept drift. In this paper, we propose a novel meta learning approach for this issue and develop a method: Multi-Step Learning (MSL). In our method, a MSL learner is structured in a recursive manner, which contains all the base learners maintained in a hierarchy, ensuring the learned concepts are traceable. We evaluated MSL and two ensemble techniques on three synthetic datasets, which contain a number of drastic concept drifts. The experimental results show that the proposed method generally performs better than the ensemble techniques in terms of prediction accuracy.

Item Type:	Book Section
Uncontrolled Keywords:	/dk/atira/pure/subjectarea/asjc/1700/1705
Departments or Groups:
Depositing User:	Admin SSL
Date Deposited:	19 Oct 2022 23:16
Last Modified:	10 Feb 2023 04:00
URI:	http://repository-testing.wit.ie/id/eprint/4965

Actions (login required)

View Item