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 51100 of 927 papers

TitleStatusHype
Graph Attention NetworksCode1
Graph Autoencoder for Graph Compression and Representation LearningCode1
Variational Recurrent Neural Networks for Graph ClassificationCode1
Approximate Network Motif Mining Via Graph LearningCode1
A Fair Comparison of Graph Neural Networks for Graph ClassificationCode1
Graph Homomorphism ConvolutionCode1
A Generalization of ViT/MLP-Mixer to GraphsCode1
Total Variation Graph Neural NetworksCode1
Agent-based Graph Neural NetworksCode1
Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message PassingCode1
Accurate Learning of Graph Representations with Graph Multiset PoolingCode1
Enhance Information Propagation for Graph Neural Network by Heterogeneous AggregationsCode1
Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric ModelsCode1
Evaluating Modules in Graph Contrastive LearningCode1
Exploring Fake News Detection with Heterogeneous Social Media Context GraphsCode1
Gated Graph Sequence Neural NetworksCode1
Edge Representation Learning with HypergraphsCode1
Global Self-Attention as a Replacement for Graph ConvolutionCode1
Efficient Graph Deep Learning in TensorFlow with tf_geometricCode1
DPPIN: A Biological Repository of Dynamic Protein-Protein Interaction Network DataCode1
Bridging the Gap Between Spectral and Spatial Domains in Graph Neural NetworksCode1
DRew: Dynamically Rewired Message Passing with DelayCode1
Discovering Invariant Rationales for Graph Neural NetworksCode1
Directional Graph NetworksCode1
TransGNN: Harnessing the Collaborative Power of Transformers and Graph Neural Networks for Recommender SystemsCode1
DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural NetworksCode1
AutoHEnsGNN: Winning Solution to AutoGraph Challenge for KDD Cup 2020Code1
A Meta-Learning Approach for Training Explainable Graph Neural NetworksCode1
Adversarial Attack on Community Detection by Hiding IndividualsCode1
Automatic Relation-aware Graph Network ProliferationCode1
AutoRDF2GML: Facilitating RDF Integration in Graph Machine LearningCode1
Backdoor Attacks to Graph Neural NetworksCode1
Efficiently predicting high resolution mass spectra with graph neural networksCode1
Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on GraphsCode1
An Empirical Study of Graph Contrastive LearningCode1
Expander Graph PropagationCode1
Adversarial Attacks on Graph Classification via Bayesian OptimisationCode1
Factorizable Graph Convolutional NetworksCode1
Fake News Detection on Social Media using Geometric Deep LearningCode1
Deep Graph Mapper: Seeing Graphs through the Neural LensCode1
Adversarial Attacks on Graph Classifiers via Bayesian OptimisationCode1
Certified Robustness of Graph Convolution Networks for Graph Classification under Topological AttacksCode1
Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer ProxiesCode1
Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral MeasuresCode1
Causal Attention for Interpretable and Generalizable Graph ClassificationCode1
CKGConv: General Graph Convolution with Continuous KernelsCode1
Global Counterfactual Explainer for Graph Neural NetworksCode1
G-Mixup: Graph Data Augmentation for Graph ClassificationCode1
Detecting Beneficial Feature Interactions for Recommender SystemsCode1
Convolutional Kernel Networks for Graph-Structured DataCode1
Show:102550
← PrevPage 2 of 19Next →

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