Theory and algorithm for learning with dissimilarity functions

Liwei Wang, Masashi Sugiyama, Cheng Yang, Kohei Hatano, Jufu Feng

研究成果: Contribution to journalLetter査読

14 被引用数 (Scopus)

抄録

We study the problem of classification when only a dissimilarity function between objects is accessible. That is, data samples are represented not by feature vectors but in terms of their pairwise dissimilarities. We establish sufficient conditions for dissimilarity functions to allow building accurate classifiers. The theory immediately suggests a learning paradigm: construct an ensemble of simple classifiers, each depending on a pair of examples; then find a convex combination of them to achieve a large margin. We next develop a practical algorithm referred to as dissimilarity- based boosting (DBoost) for learning with dissimilarity functions under theoretical guidance. Experiments on a variety of databases demonstrate that the DBoost algorithm is promising for several dissimilarity measures widely used in practice.

本文言語英語
ページ(範囲)1459-1484
ページ数26
ジャーナルNeural Computation
21
5
DOI
出版ステータス出版済み - 5 2009

All Science Journal Classification (ASJC) codes

  • Arts and Humanities (miscellaneous)
  • Cognitive Neuroscience

フィンガープリント 「Theory and algorithm for learning with dissimilarity functions」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル