AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Weighted Distillation with Unlabeled Examples

Fotis Iliopoulos, Vasilis Kontonis, Cenk Baykal, Gaurav Menghani, Khoa Trinh, Erik Vee

NeurIPS 2022 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 2 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
Reweight teacher-labeled examples with the proposed debiasing weightsStudent distillation with unlabeled examples · CIFAR-10test accuracyImproved
Reweight teacher-labeled examples with the proposed debiasing weightsStudent distillation with unlabeled examples · CIFAR-100test accuracyImproved
Reweight teacher-labeled examples with the proposed debiasing weightsStudent distillation with unlabeled examples · SVHNtest accuracyImproved
Reweight teacher-labeled examples with the proposed debiasing weightsStudent distillation with unlabeled examples · CelebA gender classificationtest accuracyImproved
Reweight teacher-labeled examples with the proposed debiasing weightsStudent distillation with unlabeled examples · ImageNettest accuracyImproved
Add the proposed example reweighting to VIDVID student distillation · CelebA gender classificationtest accuracyImproved
Update estimated weights at the end of every epoch instead of estimating them once (ablation)Weighted student distillation · CIFAR-10test accuracyImproved
Update estimated weights at the end of every epoch instead of estimating them once (ablation)Weighted student distillation · CIFAR-100test accuracyNo clear effect
Update estimated weights at the end of every epoch instead of estimating them once (ablation)Weighted student distillation · Other evaluated datasetstest accuracyImproved
Apply the proposed weighting alongside temperature scaling (ablation)Student distillation · CIFAR-100test accuracyImproved
Use temperature 2.0 and apply the proposed weighting (ablation)Student distillation · CIFAR-100test accuracyImproved

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