Multi-instance dimensionality reduction

Yu Yin Sun*, Kwok Po NG, Zhi Hua Zhou

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

11 Citations (Scopus)

Abstract

Multi-instance learning deals with problems that treat bags of instances as training examples. In single-instance learning problems, dimensionality reduction is an essential step for high-dimensional data analysis and has been studied for years. The curse of dimensionality also exists in multi-instance learning tasks, yet this difficult task has not been studied before. Direct application of existing single-instance dimensionality reduction objectives to multi-instance learning tasks may not work well since it ignores the characteristic of multi-instance learning that the labels of bags are known while the labels of instances are unknown. In this paper, we propose an effective model and develop an efficient algorithm to solve the multi-instance dimensionality reduction problem. We formulate the objective as an optimization problem by considering orthonormality and sparsity constraints in the projection matrix for dimensionality reduction, and then solve it by the gradient descent along the tangent space of the orthonormal matrices. We also propose an approximation for improving the efficiency. Experimental results validate the effectiveness of the proposed method.

Original languageEnglish
Title of host publicationAAAI-10 / IAAI-10 - Proceedings of the 24th AAAI Conference on Artificial Intelligence and the 22nd Innovative Applications of Artificial Intelligence Conference
PublisherAAAI press
Pages587-592
Number of pages6
ISBN (Print)9781577354642
Publication statusPublished - Jul 2010
Event24th AAAI Conference on Artificial Intelligence and the 22nd Innovative Applications of Artificial Intelligence Conference, AAAI-10 / IAAI-10 - Atlanta, United States, Atlanta, GA, United States
Duration: 11 Jul 201015 Jul 2010

Publication series

NameProceedings of the National Conference on Artificial Intelligence
Volume1

Conference

Conference24th AAAI Conference on Artificial Intelligence and the 22nd Innovative Applications of Artificial Intelligence Conference, AAAI-10 / IAAI-10
Country/TerritoryUnited States
CityAtlanta, GA
Period11/07/1015/07/10

Scopus Subject Areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Multi-instance dimensionality reduction'. Together they form a unique fingerprint.

Cite this