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 626650 of 927 papers

TitleStatusHype
Decimated Framelet System on Graphs and Fast G-Framelet TransformsCode0
CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning0
LCS Graph Kernel Based on Wasserstein Distance in Longest Common Subsequence Metric SpaceCode0
COPT: Coordinated Optimal Transport on Graphs0
Random Walk Graph Neural Networks0
A graph similarity for deep learning0
Certified Robustness of Graph Convolution Networks for Graph Classification under Topological AttacksCode1
A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources0
Classification by Attention: Scene Graph Classification with Prior Knowledge0
Graph-Based Neural Network Models with Multiple Self-Supervised Auxiliary Tasks0
Two-stage Training of Graph Neural Networks for Graph ClassificationCode1
Parameterized Explainer for Graph Neural NetworkCode1
Sampling and Recovery of Graph Signals based on Graph Neural Networks0
ComplexDataLab at W-NUT 2020 Task 2: Detecting Informative COVID-19 Tweets by Attending over Linked Documents0
Dark Reciprocal-Rank: Boosting Graph-Convolutional Self-Localization Network via Teacher-to-student Knowledge Transfer0
Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation LearningCode0
Graph embedding using multi-layer adjacent point merging model0
GraphMDN: Leveraging graph structure and deep learning to solve inverse problems0
Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer ProxiesCode1
Co-embedding of Nodes and Edges with Graph Neural Networks0
Line Graph Neural Networks for Link PredictionCode1
Robust Optimization as Data Augmentation for Large-scale GraphsCode1
Topology-Aware Graph Pooling Networks0
K-plex Cover Pooling for Graph Neural Networks0
Fast Graph Kernel with Optical Random FeaturesCode1
Show:102550
← PrevPage 26 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
8δ-2-LWLAccuracy85.5Unverified
9DUGNNAccuracy85.5Unverified
10CIN++Accuracy85.3Unverified