AI Paper Atlas

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

Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification

Dan dan Guo, Zhuo Li, meixi zheng, He Zhao, Mingyuan Zhou, Hongyuan Zha

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
use OT-based example re-weightingResNet-32 · CIFAR-LT-100 IF 200top-1 error: 65.30 -> 54.97Improved
use OT-based example re-weightingResNet-152 · Places-LTtop-1 error: 60.7 -> 60.32±0.02Improved
use OT-based example re-weightingResNet-50 · ImageNet-LTtop-1 error: 52.61 -> 52.36±0.01Improved
use OT-based example re-weightingBERT base uncased · SST-2 1000:10accuracy: 86.50±0.38 -> 87.10±0.05Improved
combine label and feature costs rather than using either alone (ablation)OT re-weighting · CIFAR-LT-100 IF 200top-1 error: 55.06 -> 54.97; 55.04 -> 54.97Improved
use all meta examples rather than prototypes (ablation)OT re-weighting · CIFAR-LT-100 IF 200top-1 error: 54.97 -> 54.98No clear effect
use random meta samples rather than prototypes (ablation)OT re-weighting · CIFAR-LT-100 IF 200top-1 error: 54.97 -> 55.03No clear effect
maintain and iteratively update weights rather than re-estimating from scratch (ablation)OT re-weighting · CIFAR-LT-100 IF 200top-1 error: 55.07 -> 54.97Improved
use a prototype meta distribution instead of all meta examples (ablation)OT weight net · SST-2accuracy: 86.71±0.24 -> 87.12±0.03; 86.49±0.60 -> 87.11±0.01; 86.47±0.51 -> 87.09±0.07; 86.24±0.60 -> 87.12±0.01No clear effect
use randomly sampled meta examples instead of prototypes (ablation)OT weight net · SST-2accuracy: 87.12±0.03 -> 86.59±0.50; 87.11±0.01 -> 86.14±0.52; 87.09±0.07 -> 86.08±0.77; 87.12±0.01 -> 85.85±0.52Hurt
build the meta set dynamically from imbalanced training data instead of using an additional meta set (ablation)OT weight net · SST-2accuracy: 87.08±0.09 -> 87.12±0.03; 87.13±0.04 -> 87.11±0.01; 87.14±0.08 -> 87.09±0.07; 87.10±0.05 -> 87.12±0.01No clear effect
use a weight net instead of a weight vector (ablation)OT re-weighting · ModelNet10 10:100instance accuracy: 90.40±0.17 -> 89.84±0.73Hurt

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