AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Protein Fold Classification at Scale: Benchmarking and Pretraining

Dexiong Chen, Andrei Manolache, Mathias Niepert, Karsten Borgwardt

ICML 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 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 masking at ratio 0.9 instead of 0.0 (ablation)MiAE-B · TEDBench test, linear probingmacro F1: 45.70 -> 58.52Improved
add masking at ratio 0.9 instead of 0.0 (ablation)MiAE-B · TEDBench test, fine-tuningmacro F1: 71.41 -> 73.71Improved
add inverse folding loss (ablation)MiAE-B · TEDBench test, linear probingmacro F1: 52.55 -> 58.52Improved
incorporate amino acid sequence (ablation)MiAE-B · TEDBench test, linear probingmacro F1: 58.52 -> 62.14Improved
use span masking instead of random masking (ablation)MiAE-B · TEDBench test, linear probingmacro F1: 58.52 -> 59.23No clear effect
increase decoder depth from 2 to 4 (mean pooling) (ablation)MiAE-B · TEDBench test, linear probingmacro F1: 58.52 -> 59.65Improved
increase decoder depth from 2 to 4 (CLS pooling) (ablation)MiAE-B · TEDBench test, linear probing CLSmacro F1: 34.74 -> 13.26Hurt
widen decoder from 512 to 768 (ablation)MiAE-B · TEDBench test, linear probingmacro F1: 58.52 -> 27.83Hurt
narrow decoder from 512 to 256 (ablation)MiAE-B · TEDBench test, linear probingmacro F1: 58.52 -> 35.50Hurt
scale encoder from MiAE-S to MiAE-L (ablation)MiAE · TEDBench test, linear probingmacro F1: 49.43 -> 63.50Improved
scale encoder from MiAE-S to MiAE-L (ablation)MiAE · TEDBench test, fine-tunedmacro F1: 72.28 -> 73.47No clear effect
fine-tune end to end instead of linear probingMiAE-B+seq · TEDBench testmacro F1: 62.14 -> 74.56Improved

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