SetConv: A New Approach for Learning from Imbalanced Data
EMNLP 2020, pp. 1284-1294, 2020.
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
Full Text (Upload PDF)
PPT (Upload PPT)