Molecular Property Prediction on FreeSolv

46개 결과 · ⬇ CSV · JSON

RMSE 낮을수록 좋음

Rank	Model	RMSE	R2	Paper	Code	Year
1	ESA (Edge set attention, no positional encodings)	0.595±0.013	0.977±0.001	An end-to-end attention-based approach for learning on graphs	davidbuterez/edge-set-attention	2024
2	DropGIN	0.657±0.059	0.972±0.005	DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks	karolismart/dropgnn	2021
3	GATv2	0.676±0.081	0.970±0.007	How Attentive are Graph Attention Networks?	labmlai/annotated_deep_learning_paper_implementations · rusty1s/pytorch_geometric · dmlc/dgl · +5	2021
4	GIN	0.744±0.083	0.964±0.008	How Powerful are Graph Neural Networks?	dmlc/dgl · dmlc/dgl · weihua916/powerful-gnns · +16	2018
5	GAT	0.791±0.101	0.959±0.011	Graph Attention Networks	labmlai/annotated_deep_learning_paper_implementations · dmlc/dgl · dmlc/dgl · +90	2017
6	GCN	0.815±0.086	0.957±0.009	Semi-Supervised Classification with Graph Convolutional Networks	dmlc/dgl · dmlc/dgl · tkipf/gcn · +52	2016
7	PNA	0.870±0.081	0.951±0.009	Principal Neighbourhood Aggregation for Graph Nets	rusty1s/pytorch_geometric · dmlc/dgl · lukecavabarrett/pna · +5	2020
8	TokenGT	1.038±0.125	0.930±0.018	Pure Transformers are Powerful Graph Learners	jw9730/tokengt · luis-mueller/wl-transformers	2022
9	Graphormer	1.065±0.039	0.927±0.005	Do Transformers Really Perform Bad for Graph Representation?	microsoft/Graphormer · Microsoft/Graphormer · dpstart/graphormer_new · +2	2021
10	MolGraphBench 자동 추출	1.022	–	MolGraphBench: A Benchmark of GNN Architectures for Molecular Regression Tasks		2026
11	SMA	1.09	–	Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning	johnathan-xie/sma	2024
12	ChemBFN	1.418	–	A Bayesian Flow Network Framework for Chemistry Tasks	Augus1999/bayesian-flow-network-for-chemistry	2024
13	GraphGPS	1.462±0.188	0.861±0.037	Recipe for a General, Powerful, Scalable Graph Transformer	rampasek/GraphGPS · hamed1375/exphormer · graphcore/ogb-lsc-pcqm4mv2 · +1	2022
14	Uni-Mol	1.620	–	Uni-Mol: A Universal 3D Molecular Representation Learning Framework	dptech-corp/Uni-Mol	2022
15	S-CGIB	1.648±0.074	–	Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck	NSLab-CUK/S-CGIB	2025
16	Multi-level 자동 추출	1.793	–	MMGNN: Multi-level, multi-color graph neural networks for molecular property prediction		2026
17	SPMM	1.859	–	Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model	jinhojsk515/SPMM	2022
18	ChemRL-GEM	1.877	–	ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction		2021
19	D-MPNN	2.082	–	Analyzing Learned Molecular Representations for Property Prediction	swansonk14/chemprop · jbr-ai-labs/lipophilicity-prediction · anonymous20201002/chemprop · +1	2019
20	GROVER (base)	2.176	–	Self-Supervised Graph Transformer on Large-Scale Molecular Data	deepchem/deepchem · tencent-ailab/grover · dengjianyuan/respite_mpp	2020