AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Trainable Undersampling for Class-Imbalance Learning

Minlong Peng, Qi Zhang, Xiaoyu Xing, Tao Gui, Xuanjing Huang, Yu-Gang Jiang, Keyu Ding, Zhigang Chen

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 119 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply trainable undersampling (TU) vs training on original dataSVM classifier · Two-Gaussian-Clouds testminority F1: 0.084 -> 0.396Improved
apply TU vs original dataSVM rbf · Checker board 1:50macro-F1: 0.564 -> 0.708Improved
TU vs random undersamplingvarious classifiers · Credit FraudAUCPRC: 0.860 -> 0.880Improved
TU vs RUSLR · SMS SpamF0.5: 0.938 -> 0.967Improved
TU vs cost-sensitive learningMLP · Page-blocksMCC: 0.916 vs 0.915No clear effect
add SMOTE oversampling before TU (ablation)TU · five real-world datasetstask metric: 0.915 -> 0.917 (Page-blocks)No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy