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 251300 of 927 papers

TitleStatusHype
Evaluating Link Prediction Explanations for Graph Neural NetworksCode0
Efficient Mixed Precision Quantization in Graph Neural NetworksCode0
Evolution of Graph ClassifiersCode0
CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity LearningCode0
LCS Graph Kernel Based on Wasserstein Distance in Longest Common Subsequence Metric SpaceCode0
Efficient Automatic Machine Learning via Design GraphsCode0
Are Graph Embeddings the Panacea? An Empirical Survey from the Data Fitness PerspectiveCode0
Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral EmbeddingCode0
Learnable Hypergraph Laplacian for Hypergraph LearningCode0
edGNN: a Simple and Powerful GNN for Directed Labeled GraphsCode0
Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive LearningCode0
Cell Attention NetworksCode0
Edge Classification on Graphs: New Directions in Topological ImbalanceCode0
A Canonicalization Perspective on Invariant and Equivariant LearningCode0
Kernel method for persistence diagrams via kernel embedding and weight factorCode0
Dynamic Neural Dowker Network: Approximating Persistent Homology in Dynamic Directed GraphsCode0
Catch Causal Signals from Edges for Label Imbalance in Graph ClassificationCode0
Kernel Graph Convolutional Neural NetworksCode0
k-hop Graph Neural NetworksCode0
Learnable Hypergraph Laplacian for Hypergraph LearningCode0
LightGCN: Evaluated and EnhancedCode0
Generalized Equivariance and Preferential Labeling for GNN Node ClassificationCode0
Interpretable Sparsification of Brain Graphs: Better Practices and Effective Designs for Graph Neural NetworksCode0
Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on GraphsCode0
Invariant embedding for graph classificationCode0
Capsule Graph Neural NetworkCode0
InfoGain Wavelets: Furthering the Design of Diffusion Wavelets for Graph-Structured DataCode0
IPC: A Benchmark Data Set for Learning with Graph-Structured DataCode0
DOTIN: Dropping Task-Irrelevant Nodes for GNNsCode0
DeepGCNs: Can GCNs Go as Deep as CNNs?Code0
A Persistent Weisfeiler–Lehman Procedure for Graph ClassificationCode0
Improving the interpretability of GNN predictions through conformal-based graph sparsificationCode0
Incorporating Heterophily into Graph Neural Networks for Graph ClassificationCode0
BSAL: A Framework of Bi-component Structure and Attribute Learning for Link PredictionCode0
Improving Subgraph-GNNs via Edge-Level Ego-Network EncodingsCode0
On the approximation capability of GNNs in node classification/regression tasksCode0
IsoNN: Isomorphic Neural Network for Graph Representation Learning and ClassificationCode0
Distance Metric Learning for Graph Structured DataCode0
Are Powerful Graph Neural Nets Necessary? A Dissection on Graph ClassificationCode0
Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean DatasetsCode0
A Novel Higher-order Weisfeiler-Lehman Graph ConvolutionCode0
DisenSemi: Semi-supervised Graph Classification via Disentangled Representation LearningCode0
Imbalanced Graph Classification with Multi-scale Oversampling Graph Neural NetworksCode0
Breaking Free from MMI: A New Frontier in Rationalization by Probing Input UtilizationCode0
Identity Inference on Blockchain using Graph Neural NetworkCode0
ImageNet Classification with Deep Convolutional Neural NetworksCode0
Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-SmoothingCode0
HyperAggregation: Aggregating over Graph Edges with HypernetworksCode0
An explainability framework for cortical surface-based deep learningCode0
Hunt For The Unique, Stable, Sparse And Fast Feature Learning On GraphsCode0
Show:102550
← PrevPage 6 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