Micro-MetaStream: Algorithm selection for time-changing data

• Tipo: Artigo em Revista Científica Internacional
• Data: 2021

Autores

André Luis Debiaso Rossi (Autor) Outra; Carlos Soares (Autor) FEUP; Bruno Feres de Souza (Autor) Outra; André Carlos Ponce de Leon Ferreira de Carvalho (Autor) Outra

Revista

Título: Information Sciences

Vol. 565

Páginas: 262-277

ISSN: 0020-0255

Editora: Elsevier

Indexação

ISI Web of Knowledge - 7 Citações

Scopus - 9 Citações

Outras Informações

ID Authenticus: P-00T-PDF

DOI: 10.1016/j.ins.2021.02.075

Abstract (EN): Data stream mining needs to deal with scenarios where data distribution can change over time. As a result, different learning algorithms can be more suitable in different time periods. This paper proposes micro-MetaStream, a meta-learning based method to recommend the most suitable learning algorithm for each new example arriving in a data stream. It is an evolution of MetaStream, which recommends learning algorithms for batches of examples. By using a unitary granularity, micro-MetaStream is able to respond more efficiently to changes in data distribution than its predecessor. The meta-data combines meta-features, characteristics describing recent data, with base-level features, the original variables of the new example. In experiments on real-world regression data streams, micro-metaStream outperformed MetaStream and a baseline method at the meta-level and frequently improved the predictive performance at the base-level.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 16