Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Graphs
/
Graph Classification
/
CIFAR10 100k
Graph Classification on CIFAR10 100k
Metric: Accuracy (%) (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
Sort:
Accuracy (%) (best first)
Accuracy (%) (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
Accuracy (%)
▼
Extra Data
Paper
Date
↕
Code
1
GRIT
76.468
No
Graph Inductive Biases in Transformers without M...
2023-05-27
Code
2
TIGT
73.955
No
Topology-Informed Graph Transformer
2024-02-03
Code
3
ARGNP
73.9
No
Automatic Relation-aware Graph Network Prolifera...
2022-05-31
Code
4
DGN
72.84
No
Directional Graph Networks
2020-10-06
Code
5
GPS
72.298
No
Recipe for a General, Powerful, Scalable Graph T...
2022-05-25
Code
6
PNA
70.47
No
Principal Neighbourhood Aggregation for Graph Nets
2020-04-12
Code
7
EIGENFORMER
70.194
No
Graph Transformers without Positional Encodings
2024-01-31
-
8
GatedGCN
69.37
No
Residual Gated Graph ConvNets
2017-11-20
Code
9
EGT
68.702
No
Global Self-Attention as a Replacement for Graph...
2021-08-07
Code
10
GatedGCN
67.312
No
Benchmarking Graph Neural Networks
2020-03-02
Code
11
GraphSage
66.08
No
Inductive Representation Learning on Large Graphs
2017-06-07
Code
12
GAT
65.48
No
Graph Attention Networks
2017-10-30
Code
13
MoNet
53.42
No
Geometric deep learning on graphs and manifolds ...
2016-11-25
Code
14
GIN
53.28
No
How Powerful are Graph Neural Networks?
2018-10-01
Code
#1
GRIT
SOTA
76.468
Accuracy (%)
· 2023-05-27
Graph Inductive Biases in Transformers without Message Passing
Code
#2
TIGT
73.955
Accuracy (%)
· 2024-02-03
Topology-Informed Graph Transformer
Code
#3
ARGNP
SOTA
73.9
Accuracy (%)
· 2022-05-31
Automatic Relation-aware Graph Network Proliferation
Code
#4
DGN
SOTA
72.84
Accuracy (%)
· 2020-10-06
Directional Graph Networks
Code
#5
GPS
72.298
Accuracy (%)
· 2022-05-25
Recipe for a General, Powerful, Scalable Graph Transformer
Code
#6
PNA
SOTA
70.47
Accuracy (%)
· 2020-04-12
Principal Neighbourhood Aggregation for Graph Nets
Code
#7
EIGENFORMER
70.194
Accuracy (%)
· 2024-01-31
Graph Transformers without Positional Encodings
#8
GatedGCN
SOTA
69.37
Accuracy (%)
· 2017-11-20
Residual Gated Graph ConvNets
Code
#9
EGT
68.702
Accuracy (%)
· 2021-08-07
Global Self-Attention as a Replacement for Graph Convolution
Code
#10
GatedGCN
67.312
Accuracy (%)
· 2020-03-02
Benchmarking Graph Neural Networks
Code
#11
GraphSage
SOTA
66.08
Accuracy (%)
· 2017-06-07
Inductive Representation Learning on Large Graphs
Code
#12
GAT
65.48
Accuracy (%)
· 2017-10-30
Graph Attention Networks
Code
#13
MoNet
SOTA
53.42
Accuracy (%)
· 2016-11-25
Geometric deep learning on graphs and manifolds using mixture model CNNs
Code
#14
GIN
53.28
Accuracy (%)
· 2018-10-01
How Powerful are Graph Neural Networks?
Code