Graph Classification On Imdb M

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name	Accuracy	Paper Title	Repository
DGCNN	47.83%	An End-to-End Deep Learning Architecture for Graph Classification
GraphSAGE	47.6%	A Fair Comparison of Graph Neural Networks for Graph Classification
GIN-0	52.3%	How Powerful are Graph Neural Networks?
1-WL Kernel	51.5%	Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
G-Tuning	-	Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns
U2GNN (Unsupervised)	89.2%	Universal Graph Transformer Self-Attention Networks
GIUNet	54%	Graph isomorphism UNet
Graph-JEPA	50.69%	Graph-level Representation Learning with Joint-Embedding Predictive Architectures
TREE-G	56.4%	TREE-G: Decision Trees Contesting Graph Neural Networks
MEWISPool	56.23%	Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks
GFN-light	51.20%	Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
SPI-GCN	44.13%	SPI-GCN: A Simple Permutation-Invariant Graph Convolutional Network	-
DGCNN (sum)	42.76%	An End-to-End Deep Learning Architecture for Graph Classification
UGraphEmb	50.06%	Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
k-GNN	49.5%	Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
GMT	50.66%	Accurate Learning of Graph Representations with Graph Multiset Pooling
G_ResNet	54.53%	When Work Matters: Transforming Classical Network Structures to Graph CNN	-
DropGIN	51.4%	DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks
SEG-BERT	53.4%	Segmented Graph-Bert for Graph Instance Modeling
δ-2-LWL	50.5%	Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings

0 of 35 row(s) selected.