SetConv: A New Approach for Learning from Imbalanced Data

Yi-Fan Li
Yi-Fan Li
Yu Lin
Yu Lin

empirical methods in natural language processing, pp. 1284-1294, 2020.

Cited by: 0|Bibtex|Views50|DOI:https://doi.org/10.18653/V1/2020.EMNLP-MAIN.98
Other Links: academic.microsoft.com

Abstract:

For many real-world classification problems, e.g., sentiment classification, most existing machine learning methods are biased towards the majority class when the Imbalance Ratio (IR) is high. To address this problem, we propose a set convolution (SetConv) operation and an episodic training strategy to extract a single representative for ...More

Code:

Data:

Your rating :
0

 

Tags
Comments