SOTAVerified

Unsupervised Pre-training

Pre-training a neural network using unsupervised (self-supervised) auxiliary tasks on unlabeled data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 231–240 of 265 papers

TitleStatusHype
Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation—0
Pre-training Text Representations as Meta Learning—0
Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models—0
Range-aware Positional Encoding via High-order Pretraining: Theory and Practice—0
Recognizing UMLS Semantic Types with Deep Learning—0
Representation Learning for Weakly Supervised Relation Extraction—0
Research on CPI Prediction Based on Natural Language Processing—0
Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images—0
Risk Assessment Framework for Code LLMs via Leveraging Internal States—0
R-LAtte: Attention Module for Visual Control via Reinforcement Learning—0
Show:102550
← PrevPage 24 of 27Next →
All datasetsMeaslesUCI measles

Benchmark Results

#ModelMetricClaimedVerifiedStatus
115RDLsAccuracy (%)95—Unverified
29RDLsAccuracy (%)94—Unverified
33 RMDLAccuracy (%)93—Unverified
4CNNAccuracy (%)73—Unverified
5RMDLAccuracy (%)0.1—Unverified
#ModelMetricClaimedVerifiedStatus
1RMDL (30 RDLs)Sensitivity (VEB)90.69—Unverified
2Sensitivity89.1—Unverified
3RMDL 3 RDLsSensitivity0.87—Unverified