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 401425 of 927 papers

TitleStatusHype
Template based Graph Neural Network with Optimal Transport DistancesCode0
Automatic Relation-aware Graph Network ProliferationCode1
CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity LearningCode0
Recipe for a General, Powerful, Scalable Graph TransformerCode2
High-Order Pooling for Graph Neural Networks with Tensor Decomposition0
Compressing Deep Graph Neural Networks via Adversarial Knowledge DistillationCode1
Asynchronous Neural Networks for Learning in Graphs0
GraphMAE: Self-Supervised Masked Graph AutoencodersCode2
KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classification0
Towards Explanation for Unsupervised Graph-Level Representation LearningCode2
Representation Power of Graph Neural Networks: Improved Expressivity via Algebraic Analysis0
Label-invariant Augmentation for Semi-Supervised Graph Classification0
Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis0
GraphHD: Efficient graph classification using hyperdimensional computingCode1
Orthogonal Gromov-Wasserstein Discrepancy with Efficient Lower BoundCode0
NDGGNET-A Node Independent Gate based Graph Neural Networks0
Spatial-temporal associations representation and application for process monitoring using graph convolution neural network0
Data-Free Adversarial Knowledge Distillation for Graph Neural Networks0
Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical GuaranteesCode0
Clustered Graph Matching for Label Recovery and Graph Classification0
Spiking Graph Convolutional NetworksCode1
FAITH: Few-Shot Graph Classification with Hierarchical Task GraphsCode1
HL-Net: Heterophily Learning Network for Scene Graph GenerationCode1
FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation0
DOTIN: Dropping Task-Irrelevant Nodes for GNNsCode0
Show:102550
← PrevPage 17 of 38Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GIN-0Accuracy762Unverified
2HGP-SLAccuracy84.91Unverified
3rLap (unsupervised)Accuracy84.3Unverified
4TFGW ADJ (L=2)Accuracy82.9Unverified
5FIT-GNNAccuracy82.1Unverified
6DUGNNAccuracy81.7Unverified
7MEWISPoolAccuracy80.71Unverified
8CIN++Accuracy80.5Unverified
9MAGPoolAccuracy80.36Unverified
10SAEPoolAccuracy80.36Unverified
#ModelMetricClaimedVerifiedStatus
1Evolution of Graph ClassifiersAccuracy100Unverified
2MEWISPoolAccuracy96.66Unverified
3TFGW ADJ (L=2)Accuracy96.4Unverified
4GIUNetAccuracy95.7Unverified
5G_InceptionAccuracy95Unverified
6GICAccuracy94.44Unverified
7CIN++Accuracy94.4Unverified
8sGINAccuracy94.14Unverified
9CANAccuracy94.1Unverified
10Deep WL SGN(0,1,2)Accuracy93.68Unverified
#ModelMetricClaimedVerifiedStatus
1TFGW ADJ (L=2)Accuracy88.1Unverified
2WKPI-kmeansAccuracy87.2Unverified
3FGW wl h=4 spAccuracy86.42Unverified
4WL-OA KernelAccuracy86.1Unverified
5WL-OAAccuracy86.1Unverified
6FGW wl h=2 spAccuracy85.82Unverified
7WWLAccuracy85.75Unverified
8DUGNNAccuracy85.5Unverified
9δ-2-LWLAccuracy85.5Unverified
10CIN++Accuracy85.3Unverified