paper-with-me

홈 › Papers

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

2021-06-17 · Arpit Bansal, Micah Goldblum, Valeriia Cherepanova, Avi Schwarzschild, C. Bayan Bruss, Tom Goldstein

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.

📄 PDF Abstract BibTeX arXiv:2106.09643

Code (0)

등록된 구현이 없습니다.

Tasks

Fraud Detectionimage-classificationImage ClassificationMemorizationMeta-LearningVocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks

2022-03-14 · Yun He, Xue Feng, Cheng Cheng, Geng Ji 외

In many personalized recommendation scenarios, the generalization ability of a target task can be improved via learning with additional auxiliary tasks alongside this target task on a multi-task network. However, this me…

Predicting Louisiana Public High School Dropout through Imbalanced Learning Techniques

2019-10-29 · Marmar Orooji, Jianhua Chen

This study is motivated by the magnitude of the problem of Louisiana high school dropout and its negative impacts on individual and public well-being. Our goal is to predict students who are at risk of high school dropou…

Vocal Bursts Intensity Prediction

Imbalanced Ensemble Classifier for learning from imbalanced business school data set

2018-05-31 · Tanujit Chakraborty

Private business schools in India face a common problem of selecting quality students for their MBA programs to achieve the desired placement percentage. Generally, such data sets are biased towards one class, i.e., imba…

feature selectionGeneral Classification

GenSample: A Genetic Algorithm for Oversampling in Imbalanced Datasets

2019-10-23 · Vishwa Karia, Wen-Hao Zhang, Arash Naeim, Ramin Ramezani

Imbalanced datasets are ubiquitous. Classification performance on imbalanced datasets is generally poor for the minority class as the classifier cannot learn decision boundaries well. However, in sensitive applications l…

Fraud DetectionMedical Diagnosis

Exploring "Many in Few" and "Few in Many" Properties in Long-Tailed, Highly-Imbalanced IC Defect Classification

2025-10-22 · Hao-Chiang Shao, Chun-Hao Chang, Yu-Hsien Lin, Chia-Wen Lin 외 arxiv

Despite significant advancements in deep classification techniques and in-lab automatic optical inspection models for long-tailed or highly imbalanced data, applying these approaches to real-world IC defect classificatio…

Knowledge DistillationMetric Learning