HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Graph Classification On Mnist

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name
Accuracy
Paper TitleRepository
GCN+98.382 ± 0.095Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence-
EIGENFORMER98.362Graph Transformers without Positional Encodings-
NeuralWalker98.760 ± 0.079Learning Long Range Dependencies on Graphs via Random Walks-
GatedGCN97.340Benchmarking Graph Neural Networks-
EGT98.173Global Self-Attention as a Replacement for Graph Convolution-
Exphormer98.414±0.038Exphormer: Sparse Transformers for Graphs-
ESA (Edge set attention, no positional encodings)98.753±0.041An end-to-end attention-based approach for learning on graphs-
GPS98.05Recipe for a General, Powerful, Scalable Graph Transformer-
CKGCN98.423CKGConv: General Graph Convolution with Continuous Kernels-
TIGT98.230±0.133Topology-Informed Graph Transformer-
GatedGCN+98.712 ± 0.137Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence-
GRIT98.108Graph Inductive Biases in Transformers without Message Passing-
ESA (Edge set attention, no positional encodings, tuned)98.917±0.020An end-to-end attention-based approach for learning on graphs-
0 of 13 row(s) selected.
Graph Classification On Mnist | SOTA | HyperAI