Graph Property Prediction on QM9

Metric: gap (meV) (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	gap (meV)▼	Extra Data	Paper	Date↕	Code
1	EGNN	48	No	E(n) Equivariant Graph Neural Networks	2021-02-19	Code
2	SEGNN	42	No	Geometric and Physical Quantities Improve E(3) E...	2021-10-06	Code
3	TorchMD-NET	36.1	No	TorchMD-NET: Equivariant Transformers for Neural...	2022-02-05	Code
4	Geoformer	33.8	No	-	-	-
5	EQGAT	32	No	-	-	-
6	Equiformer	30	No	Equiformer: Equivariant Graph Attention Transfor...	2022-06-23	Code
7	EquiformerV2	29	No	EquiformerV2: Improved Equivariant Transformer f...	2023-06-21	Code
8	GotenNet (Small)	21.2	No	-	-	Code
9	GotenNet (Base)	20.5	No	-	-	Code
10	GotenNet (Large)	19.8	No	-	-	Code

#1EGNNSOTA
48
gap (meV)· 2021-02-19
E(n) Equivariant Graph Neural Networks Code
#2SEGNN
42
gap (meV)· 2021-10-06
Geometric and Physical Quantities Improve E(3) Equivariant Message Passing Code
#3TorchMD-NET
36.1
gap (meV)· 2022-02-05
TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials Code
#4Geoformer
33.8
gap (meV)
No paper
#5EQGAT
32
gap (meV)
No paper
#6Equiformer
30
gap (meV)· 2022-06-23
Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs Code
#7EquiformerV2
29
gap (meV)· 2023-06-21
EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations Code
#8GotenNet (Small)
21.2
gap (meV)
No paperCode
#9GotenNet (Base)
20.5
gap (meV)
No paperCode
#10GotenNet (Large)
19.8
gap (meV)
No paperCode