AI Paper Atlas

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

Parallel-mentoring for Offline Model-based Optimization

Can Chen, Christopher Beckham, Zixuan Liu, Xue Liu, Christopher Pal

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 0 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
add voting-based pairwise supervision (vs mean-ensemble labels) (ablation)tri-mentoring · Design-Bench NASmax normalized score: 0.509 -> 0.759Improved
add voting-based pairwise supervision (vs mean-ensemble labels) (ablation)tri-mentoring · Design-Bench Hopper Controllermax normalized score: 1.902 -> 1.983Improved
add voting-based pairwise supervision (vs mean-ensemble labels) (ablation)tri-mentoring · Design-Bench TF Bind 8max normalized score: 0.971 -> 0.970No clear effect
add adaptive soft-labeling (vs one-hot consensus labels) (ablation)tri-mentoring · Design-Bench NASmax normalized score: 0.538 -> 0.759Improved
add adaptive soft-labeling (vs one-hot consensus labels) (ablation)tri-mentoring · Design-Bench TF Bind 8max normalized score: 0.944 -> 0.970Improved
add neighborhood sampling around the optimization point (ablation)tri-mentoring · Design-Bench Hopper Controllermax normalized score: 1.839 -> 1.983Improved
add neighborhood sampling around the optimization point (ablation)tri-mentoring · Design-Bench Superconductormax normalized score: 0.516 -> 0.514No clear effect
proxies exchange ranking signals instead of post selection (ablation)tri-mentoring · Design-Bench TF Bind 10max normalized score: 0.635 -> 0.722Improved
proxies exchange ranking signals instead of post selection (ablation)tri-mentoring · Design-Bench D'Kitty Morphologymax normalized score: 0.970 -> 0.966No clear effect
add voting-based supervision on label accuracy of conflicting labels (ablation)tri-mentoring · D'Kitty pairwise labelsaccuracy of conflicting labels (%): 52.21% -> 62.91%Improved
add adaptive soft-labeling on label accuracy of conflicting labels (ablation)tri-mentoring · TFB8 pairwise labelsaccuracy of conflicting labels (%): 60.86% -> 63.16%Improved
combine COMs with tri-mentoringtri-mentoring · Ant Morphology / TF Bind 8max normalized score: 0.948 -> 0.941 (Ant), 0.970 -> 0.960 (TFB8)Hurt

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