# SetConv: A New Approach for Learning from Imbalanced Data

arXiv: https://arxiv.org/abs/2104.06313 · HTML: https://mlsanity.com/paper/2104.06313/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 34 references that are in the map.
- First posted on arXiv 3 Apr 2021.

## Builds on (most cited first, 5 of 5)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [SemEval-2017 Task 4: Sentiment Analysis in Twitter](https://mlsanity.com/paper/1912.00741/) (2019)
- [Introduction to Tensor Decompositions and their Applications in Machine Learning](https://mlsanity.com/paper/1711.10781/) (2017)
- [Oversampling for Imbalanced Learning Based on K-Means and SMOTE](https://mlsanity.com/paper/1711.00837/) (2017)

## Built on by (most cited first, 3 of 3)

- [A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing](https://mlsanity.com/paper/2210.04675/) (2022)
- [Distance-wise Prototypical Graph Neural Network in Node Imbalance Classification](https://mlsanity.com/paper/2110.12035/) (2021)
- [APAM: Adaptive Pre-training and Adaptive Meta Learning in Language Model for Noisy Labels and Long-tailed Learning](https://mlsanity.com/paper/2302.03488/) (2023)

## Abstract (arXiv)

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.