Back to Search
Start Over
LRID: A new metric of multi-class imbalance degree based on likelihood-ratio test
- Source :
- Pattern Recognition Letters. 116:36-42
- Publication Year :
- 2018
- Publisher :
- Elsevier BV, 2018.
-
Abstract
- In this paper, we introduce a new likelihood ratio imbalance degree (LRID) to measure the class-imbalance extent of multi-class data. Imbalance ratio (IR) is usually used to measure class-imbalance extent in imbalanced learning problems. However, IR cannot capture the detailed information in the class distribution of multi-class data, because it only utilises the information of the largest majority class and the smallest minority class. Imbalance degree (ID) has been proposed to solve the problem of IR for multi-class data. However, we note that improper use of distance metric in ID can have harmful effect on the results. In addition, ID assumes that data with more minority classes are more imbalanced than data with less minority classes, which is not always true in practice. Thus ID cannot provide reliable measurement when the assumption is violated. In this paper, we propose a new metric based on the likelihood-ratio test, LRID, to provide a more reliable measurement of class-imbalance extent for multi-class data. Experiments on both simulated and real data show that LRID is competitive with IR and ID, and can reduce the negative correlation with F1 scores by up to 0.55.
- Subjects :
- Degree (graph theory)
Computer science
HA
02 engineering and technology
Minority class
01 natural sciences
Class (biology)
Measure (mathematics)
Class imbalance
Distribution (mathematics)
Artificial Intelligence
Likelihood-ratio test
0103 physical sciences
Signal Processing
Statistics
Metric (mathematics)
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
010306 general physics
Software
Subjects
Details
- ISSN :
- 01678655
- Volume :
- 116
- Database :
- OpenAIRE
- Journal :
- Pattern Recognition Letters
- Accession number :
- edsair.doi.dedup.....51678a66c0fdd848a7ef1ee66bb57ac9