Extracting Label Importance Information for Multi-label Classification

Zhang, X 2018, 'Extracting Label Importance Information for Multi-label Classification', in Database Systems for Advanced Applications. DASFAA 2018., Gold Coast, Australia, 21-24 May 2018, pp. 424-439.


Document type: Conference Paper
Collection: Conference Papers

Title Extracting Label Importance Information for Multi-label Classification
Author(s) Zhang, X
Year 2018
Conference name 23rd International Conference on Database Systems for Advanced Applications
Conference location Gold Coast, Australia
Conference dates 21-24 May 2018
Proceedings title Database Systems for Advanced Applications. DASFAA 2018.
Publisher Springer
Place of publication Switzerland
Start page 424
End page 439
Total pages 16
Abstract Existing multi-label learning approaches assume all labels in a dataset are of the same importance. However, the importance of each label is generally different in real world. In this paper, we introduce multi-label importance (MLI) which measures label importance from two perspectives: label predictability and label effects. Specifically, label predictability and label effects can be extracted from training data before building models for multi-label learning. After that, the multi-label importance information can be used in existing approaches to improve the performance of multi-label learning. To prove this, we propose a classifier chain algorithm based on multi-label importance ranking and a improved kNN-based algorithm which takes both feature distance and label distance into consideration. We apply our algorithms on benchmark datasets demonstrating efficient multi-label learning by exploiting multi-label importance. It is also worth mentioning that our experiments show the strong positive correlation between label predictability and label effects.
Subjects Information Systems Management
ISBN 9783319914572
Versions
Version Filter Type
Access Statistics: 23 Abstract Views  -  Detailed Statistics
Created: Thu, 21 Feb 2019, 12:10:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us