AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Learning to Auto Weight: Entirely Data-Driven and Highly Efficient Weighting Framework

Zhenmao Li, Yichao Wu, Ken Chen, Yudong Wu, Shunfeng Zhou, Jiaheng Liu, Jiaheng Liu, Junjie Yan

AAAI 2020 · Architectures and efficiency › Neural architecture search · approach: AutoML pipeline search · 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
Apply learned LAW example weighting instead of equal sample weightingResNet-18 · CIFAR-10-Noisytop-1 accuracy: 79.44 -> 86.33Improved
Apply learned LAW example weighting instead of equal sample weightingWRN-28-10 · CIFAR-100-Noisytop-1 accuracy: 53.11 -> 68.23Improved
Use LAW rather than MentorNetWRN-28-10 · CIFAR-10-Noisytop-1 accuracy: 87.56 -> 89.73Improved
Use LAW rather than MentorNetWRN-28-10 · CIFAR-100-Noisytop-1 accuracy: 65.56 -> 68.23Improved
Apply learned LAW example weighting instead of equal sample weightingResNet-50 · Noisy ImageNettop-1 accuracy: 71.9 -> 73.7Improved
Apply learned LAW example weighting instead of equal sample weightingVGG-19 · CIFAR-10-Imbalancetop-1 accuracy: 84.88 -> 85.33Improved
Use LAW rather than L2RWResNet-32 · CIFAR-100-Imbalancetop-1 accuracy: 41.23 -> 43.61Improved
Increase weights for samples in minority classesLAW · CIFAR imbalance datasetssample weightImproved
Reduce weights for corrupted-label samplesLAW · Noisy CIFAR and ImageNettraining loss gapImproved

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