# MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data

Source: [MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data](<https://www.sota2.com/research/paper/68fa6a281e209131cea266f5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:18:37.363Z

Authors: Arpit Bansal, Micah Goldblum, Valeriia Cherepanova, Avi Schwarzschild, C. Bayan Bruss, Tom Goldstein

Published: 2021-06-17T16:42:50.000Z

## Abstract

Class-imbalanced data, in which some classes contain far more samples than others, is ubiquitous in real-world applications. Standard techniques for handling class-imbalance usually work by training on a re-weighted loss or on re-balanced data. Unfortunately, training overparameterized neural networks on such objectives causes rapid memorization of minority class data. To avoid this trap, we harness meta-learning, which uses both an ''outer-loop'' and an ''inner-loop'' loss, each of which may be balanced using different strategies. We evaluate our method, MetaBalance, on image classification, credit-card fraud detection, loan default prediction, and facial recognition tasks with severely imbalanced data, and we find that MetaBalance outperforms a wide array of popular re-sampling strategies.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2106.09643>)

[PDF](<https://arxiv.org/pdf/2106.09643.pdf>)