الرئيسية الأخبار الأوراق البحثية الدروس مجموعات البيانات الموسوعة SOTA نماذج LLM لوحة الأداء GPU الفعاليات

العربية

Molecular Property Prediction On

المقاييس

RMSE

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	RMSE	Paper Title	Repository
N-GramRF	0.812	N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
SMA	0.609	Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning
ChemBERTa-2 (MTR-77M)	0.798	ChemBERTa-2: Towards Chemical Foundation Models
GROVER (large)	0.823	Self-Supervised Graph Transformer on Large-Scale Molecular Data
D-MPNN	0.683	Analyzing Learned Molecular Representations for Property Prediction
N-GramXGB	2.072	N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
GROVER (base)	0.817	Self-Supervised Graph Transformer on Large-Scale Molecular Data
SPMM	0.706	Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model
Uni-Mol	0.603	Uni-Mol: A Universal 3D Molecular Representation Learning Framework	-
ChemBFN	0.746	A Bayesian Flow Network Framework for Chemistry Tasks
S-CGIB	0.762±0.042	Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck	-
ChemRL-GEM	0.66	ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction	-
PretrainGNN	0.739	Strategies for Pre-training Graph Neural Networks

0 of 13 row(s) selected.