SetConv: A New Approach for Learning from Imbalanced Data

Yang Gao, Yi-Fan Li, Yu Lin, Charu Aggarwal, Latifur Khan


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 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.
Anthology ID:
2020.emnlp-main.98
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1284–1294
Language:
URL:
https://aclanthology.org/2020.emnlp-main.98
DOI:
10.18653/v1/2020.emnlp-main.98
Bibkey:
Cite (ACL):
Yang Gao, Yi-Fan Li, Yu Lin, Charu Aggarwal, and Latifur Khan. 2020. SetConv: A New Approach for Learning from Imbalanced Data. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1284–1294, Online. Association for Computational Linguistics.
Cite (Informal):
SetConv: A New Approach for Learning from Imbalanced Data (Gao et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.emnlp-main.98.pdf