Classifier chains for multi-label classification

The widely known binary relevance method for multi-label classification, which considers each label as an independent binary problem, has often been overlooked in the literature due to the perceived inadequacy of not directly modelling label correlations. Most current methods invest considerable com...

Full description

Saved in:
Bibliographic Details
Published in:Machine learning Vol. 85; no. 3; pp. 333 - 359
Main Authors: Read, Jesse, Pfahringer, Bernhard, Holmes, Geoff, Frank, Eibe
Format: Journal Article
Language:English
Published: Boston Springer US 01.12.2011
Springer
Springer Nature B.V
Subjects:
Acceptability
Algorithmics. Computability. Computer arithmetics
Applied sciences
Artificial Intelligence
Chaining
Classification
Classifiers
Complexity
Computer Science
Computer science; control theory; systems
Computer systems and distributed systems. User interface
Control
Correlation
Data processing. List processing. Character string processing
Exact sciences and technology
Information systems. Data bases
Labels
Mathematical models
Mathematical problems
Mechatronics
Memory organisation. Data processing
Natural Language Processing (NLP)
Robotics
Simulation and Modeling
Software
Theoretical computing
Problem transformation
Scalable methods
Ensemble methods
Multi-label classification
High performance
Data analysis
Automatic classification
Scalability
Competitiveness
Very large databases
Computational complexity
Modeling
Aggregate model
Relevance
Model matching
Supervised learning
Metric
Time complexity
ISSN:0885-6125, 1573-0565
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The widely known binary relevance method for multi-label classification, which considers each label as an independent binary problem, has often been overlooked in the literature due to the perceived inadequacy of not directly modelling label correlations. Most current methods invest considerable complexity to model interdependencies between labels. This paper shows that binary relevance-based methods have much to offer, and that high predictive performance can be obtained without impeding scalability to large datasets. We exemplify this with a novel classifier chains method that can model label correlations while maintaining acceptable computational complexity. We extend this approach further in an ensemble framework. An extensive empirical evaluation covers a broad range of multi-label datasets with a variety of evaluation metrics. The results illustrate the competitiveness of the chaining method against related and state-of-the-art methods, both in terms of predictive performance and time complexity.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0885-6125
1573-0565
DOI:10.1007/s10994-011-5256-5