AI Paper Atlas

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

Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels

Yu-Ting Chou, Gang Niu, Hsuan-Tien Lin, Masashi Sugiyama

ICML 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 14 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 SCL-EXP instead of URELinear model · MNISTaccuracy: 0.8503 -> 0.9019Improved
Use SCL-NL instead of GAMLP · MNISTaccuracy: 0.9088 -> 0.9469Improved
Use SCL-EXP instead of URELinear model · Kuzushi-MNISTaccuracy: 0.5613 -> 0.6132Improved
Use SCL-NL instead of GAMLP · Kuzushi-MNISTaccuracy: 0.6567 -> 0.7644Improved
Use SCL-EXP instead of NNLinear model · Fashion-MNISTaccuracy: 0.7755 -> 0.8282Improved
Use SCL-NL instead of GAMLP · Fashion-MNISTaccuracy: 0.8019 -> 0.8456Improved
Use SCL-FWD instead of GAResnet · CIFAR-10accuracy: 0.3738 -> 0.5058Improved
Use SCL-FWD instead of GADenseNet · CIFAR-10accuracy: 0.4108 -> 0.5457Improved
Replace URE with SCL-FWD for gradient estimationLinear model · MNISTgradient MSE: 1.9692E-03 -> 7.7511E-06Improved
Replace URE with SCL-FWD for gradient estimationDenseNet · CIFAR-10gradient MSE: 5.0196E-02 -> 2.0237E-04Improved

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