SOTAVerified

Graph Classification

Graph Classification is a task that involves classifying a graph-structured data into different classes or categories. Graphs are a powerful way to represent relationships and interactions between different entities, and graph classification can be applied to a wide range of applications, such as social network analysis, bioinformatics, and recommendation systems. In graph classification, the input is a graph, and the goal is to learn a classifier that can accurately predict the class of the graph.

( Image credit: Hierarchical Graph Pooling with Structure Learning )

Papers

Showing 1–10 of 927 papers

TitleStatusHype
Density-aware Walks for Coordinated Campaign DetectionCode0
Positional Encoding meets Persistent Homology on GraphsCode0
Weisfeiler and Leman Follow the Arrow of Time: Expressive Power of Message Passing in Temporal Event Graphs—0
Improving the Effective Receptive Field of Message-Passing Neural NetworksCode1
Graph Style Transfer for Counterfactual ExplainabilityCode0
Scalable Graph Generative Modeling via Substructure SequencesCode0
Addressing the Scarcity of Benchmarks for Graph XAICode0
Schreier-Coset Graph Propagation—0
Efficient Mixed Precision Quantization in Graph Neural NetworksCode0
Rhomboid Tiling for Geometric Graph Deep Learning—0
Show:102550
← PrevPage 1 of 93Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1U2GNN (Unsupervised)Accuracy95.62—Unverified
2TFGW ADJ (L=2)Accuracy84.3—Unverified
3DUGNNAccuracy84.2—Unverified
4G_DenseNetAccuracy83.16—Unverified
5GFNAccuracy81.5—Unverified
6PPGNAccuracy81.38—Unverified
7GFN-lightAccuracy81.34—Unverified
8FactorGCNAccuracy81.2—Unverified
9GMTAccuracy80.74—Unverified
10sGINAccuracy80.71—Unverified