SetConv: A New Approach for Learning from Imbalanced Data
Gao, Yang, Li, Yi-Fan, Lin, Yu, Aggarwal, Charu, Khan, Latifur
–arXiv.org Artificial Intelligence
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 each class, so that classifiers can later be trained on a balanced class distribution. We prove that our proposed algorithm is permutation-invariant despite the order of inputs, and experiments on multiple large-scale benchmark text datasets show the superiority of our proposed framework when compared to other SOTA methods.
arXiv.org Artificial Intelligence
Apr-3-2021
- Country:
- South America > Brazil (0.04)
- North America
- United States
- Texas (0.04)
- New York (0.04)
- Nevada > Clark County
- Las Vegas (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Illinois > Cook County
- Chicago (0.04)
- California > San Francisco County
- San Francisco (0.28)
- Canada > Quebec
- Montreal (0.04)
- United States
- Europe
- Asia > Japan
- Honshū > Tōhoku > Miyagi Prefecture > Sendai (0.04)
- Genre:
- Research Report (0.82)
- Technology: