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 551600 of 927 papers

TitleStatusHype
Relation order histograms as a network embedding toolCode0
Do Transformers Really Perform Bad for Graph Representation?Code2
Learning subtree pattern importance for Weisfeiler-Lehmanbased graph kernelsCode0
Graph2Graph Learning with Conditional Autoregressive Models0
Convergent Graph SolversCode1
Mixup for Node and Graph ClassificationCode1
How Attentive are Graph Attention Networks?Code1
Self-Supervised Graph Representation Learning via Topology TransformationsCode0
Revisiting 2D Convolutional Neural Networks for Graph-based Applications0
Multi-task Graph Convolutional Neural Network for Calcification Morphology and Distribution Analysis in Mammograms0
Graph Neural Networks for Inconsistent Cluster Detection in Incremental Entity Resolution0
Structure-Aware Hierarchical Graph Pooling using Information BottleneckCode0
User Preference-aware Fake News DetectionCode1
Permutation-Invariant Variational Autoencoder for Graph-Level Representation LearningCode1
Quadratic GCN for Graph ClassificationCode0
Identity Inference on Blockchain using Graph Neural NetworkCode0
A Hyperbolic-to-Hyperbolic Graph Convolutional Network0
Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning0
Smart Vectorizations for Single and Multiparameter PersistenceCode0
Scaling up graph homomorphism for classification via sampling0
GABO: Graph Augmentations with Bi-level Optimization0
Parameterized Hypercomplex Graph Neural Networks for Graph ClassificationCode1
Unified Graph Structured Models for Video Understanding0
Graph Classification by Mixture of Diverse Experts0
Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph ClassificationCode1
GraphDIVE: Graph Classification by Mixture of Diverse ExpertsCode0
Learning to Represent the Evolution of Dynamic Graphs with Recurrent Models0
Diversified Multiscale Graph Learning with Graph Self-Correction0
Should Graph Neural Networks Use Features, Edges, Or Both?0
Scaling Up Graph Homomorphism Features with Efficient Data Structures0
Sanity Check for Persistence Diagrams0
Size-Invariant Graph Representations for Graph Classification ExtrapolationsCode1
Structure-Enhanced Meta-Learning For Few-Shot Graph ClassificationCode0
Graph Autoencoder for Graph Compression and Representation LearningCode1
Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities0
CogDL: A Comprehensive Library for Graph Deep LearningCode2
Graphfool: Targeted Label Adversarial Attack on Graph Embedding0
Generalized Equivariance and Preferential Labeling for GNN Node ClassificationCode0
Accurate Learning of Graph Representations with Graph Multiset PoolingCode1
Ego-based Entropy Measures for Structural Representations on Graphs0
Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message PassingCode1
Reinforcement Learning For Data Poisoning on Graph Neural Networks0
Online Graph Dictionary LearningCode1
Improving Scene Graph Classification by Exploiting Knowledge from Texts0
Enhance Information Propagation for Graph Neural Network by Heterogeneous AggregationsCode1
Learning Graph Representations0
Graph Classification Based on Skeleton and Component Features0
[Re] Parameterized Explainer for Graph Neural NetworkCode1
Efficient Graph Deep Learning in TensorFlow with tf_geometricCode1
Identity-aware Graph Neural NetworksCode2
Show:102550
← PrevPage 12 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
8δ-2-LWLAccuracy85.5Unverified
9DUGNNAccuracy85.5Unverified
10CIN++Accuracy85.3Unverified