Graph Classification On Imdb B

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Accuracy	Paper Title	Repository
GMT	73.48%	Accurate Learning of Graph Representations with Graph Multiset Pooling	-
DropGIN	75.7%	DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks	-
G-Tuning	-	Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns	-
k-GNN	74.2%	Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks	-
ESA (Edge set attention, no positional encodings)	86.250±0.957	An end-to-end attention-based approach for learning on graphs	-
Deep WL SGN(0,1,2)	75.70%	Subgraph Networks with Application to Structural Feature Space Expansion	-
TokenGT	80.250±3.304	Pure Transformers are Powerful Graph Learners	-
GIUNet	76%	Graph isomorphism UNet
WKPI-kcenters	75.4%	Learning metrics for persistence-based summaries and applications for graph classification	-
DGK	66.96%	Deep Graph Kernels	-
GIN-0	75.1%	How Powerful are Graph Neural Networks?	-
GraphGPS	79.250±3.096	Recipe for a General, Powerful, Scalable Graph Transformer	-
SEG-BERT	77.2%	Segmented Graph-Bert for Graph Instance Modeling	-
U2GNN	77.04%	Universal Graph Transformer Self-Attention Networks	-
G_ResNet	79.90%	When Work Matters: Transforming Classical Network Structures to Graph CNN	-
PPGN	72.6%	Provably Powerful Graph Networks	-
GCAPS-CNN	71.69%	Graph Capsule Convolutional Neural Networks	-
AWE	74.45%	Anonymous Walk Embeddings	-
GraphSAGE	68.8%	A Fair Comparison of Graph Neural Networks for Graph Classification	-
DGCNN (sum)	51.69%	An End-to-End Deep Learning Architecture for Graph Classification

0 of 50 row(s) selected.