Weighted Competitive-Collaborative Representation Based Classifier for Imbalanced Data Classification
Lists
Only you see this
Abstract
Competitive-collaborative representation based classification (CCRC) has been widely used in pattern recognition and machine learning due to its simplicity, effectiveness, and low complexity. However, its performance is highly dependent on the data distribution. When addressing imbalanced classification issue, its classification results usually tend towards the majority classes. To solve this deficiency, a class weight learning algorithm is introduced into the framework of CCRC for imbalanced classification. The weight of each class is adaptively generated according to the representation ability of each class of training samples, in which the minority classes can be given larger weights. Our proposed model is solved with a closed-form solution and inherits the efficiency property of CCRC. Extensive experimental results show that our model outperforms the commonly used imbalanced classification methods.
BibTeX
@inproceedings{li2022weighted,
author = {Yanting Li and Shuai Wang and Junwei Jin and C. L. Philip Chen},
title = {{Weighted Competitive-Collaborative Representation Based Classifier for Imbalanced Data Classification}},
booktitle = {CICAI},
year = {2022},
url = {https://openreview.net/forum?id=IzoHz0sCbc},
}Loading related content...