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 1–50 of 927 papers

TitleStatusHype
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question AnsweringCode4
Molecular Fingerprints Are Strong Models for Peptide Function PredictionCode3
SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline KernelsCode3
Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet ExcellenceCode2
Explanation-Preserving Augmentation for Semi-Supervised Graph Representation LearningCode2
KAGNNs: Kolmogorov-Arnold Networks meet Graph LearningCode2
Dynamic GNNs for Precise Seizure Detection and Classification from EEG DataCode2
Gradformer: Graph Transformer with Exponential DecayCode2
An end-to-end attention-based approach for learning on graphsCode2
One for All: Towards Training One Graph Model for All Classification TasksCode2
Hypergraph Isomorphism ComputationCode2
Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product NetworksCode2
Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Dataset Augmented by ChatGPTCode2
Recipe for a General, Powerful, Scalable Graph TransformerCode2
GraphMAE: Self-Supervised Masked Graph AutoencodersCode2
Towards Explanation for Unsupervised Graph-Level Representation LearningCode2
Do Transformers Really Perform Bad for Graph Representation?Code2
CogDL: A Comprehensive Library for Graph Deep LearningCode2
Identity-aware Graph Neural NetworksCode2
Graph Neural Networks in TensorFlow and Keras with SpektralCode2
Benchmarking Graph Neural NetworksCode2
Optimal Transport for structured data with application on graphsCode2
Improving the Effective Receptive Field of Message-Passing Neural NetworksCode1
Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information BottleneckCode1
Beyond Message Passing: Neural Graph Pattern MachineCode1
Semi-Implicit Neural Ordinary Differential EquationsCode1
Training MLPs on Graphs without SupervisionCode1
GrokFormer: Graph Fourier Kolmogorov-Arnold TransformersCode1
RAGraph: A General Retrieval-Augmented Graph Learning FrameworkCode1
Vector-ICL: In-context Learning with Continuous Vector RepresentationsCode1
AutoRDF2GML: Facilitating RDF Integration in Graph Machine LearningCode1
A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and GeneralizabilityCode1
How Interpretable Are Interpretable Graph Neural Networks?Code1
PANDA: Expanded Width-Aware Message Passing Beyond RewiringCode1
Learning Long Range Dependencies on Graphs via Random WalksCode1
Spatio-Spectral Graph Neural NetworksCode1
Node Identifiers: Compact, Discrete Representations for Efficient Graph LearningCode1
Perception-Inspired Graph Convolution for Music Understanding TasksCode1
CKGConv: General Graph Convolution with Continuous KernelsCode1
Graph Parsing NetworksCode1
SimMLP: Training MLPs on Graphs without SupervisionCode1
A Graph is Worth K Words: Euclideanizing Graph using Pure TransformerCode1
Topology-Informed Graph TransformerCode1
Graph Contrastive Learning with Cohesive Subgraph AwarenessCode1
View-based Explanations for Graph Neural NetworksCode1
Fine-tuning Graph Neural Networks by Preserving Graph Generative PatternsCode1
Recurrent Distance Filtering for Graph Representation LearningCode1
Graph-level Representation Learning with Joint-Embedding Predictive ArchitecturesCode1
Where Did the Gap Go? Reassessing the Long-Range Graph BenchmarkCode1
TransGNN: Harnessing the Collaborative Power of Transformers and Graph Neural Networks for Recommender SystemsCode1
Show:102550
← PrevPage 1 of 19Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GIN-0Accuracy762—Unverified
2HGP-SLAccuracy84.91—Unverified
3rLap (unsupervised)Accuracy84.3—Unverified
4TFGW ADJ (L=2)Accuracy82.9—Unverified
5FIT-GNNAccuracy82.1—Unverified
6DUGNNAccuracy81.7—Unverified
7MEWISPoolAccuracy80.71—Unverified
8CIN++Accuracy80.5—Unverified
9MAGPoolAccuracy80.36—Unverified
10SAEPoolAccuracy80.36—Unverified
#ModelMetricClaimedVerifiedStatus
1Evolution of Graph ClassifiersAccuracy100—Unverified
2MEWISPoolAccuracy96.66—Unverified
3TFGW ADJ (L=2)Accuracy96.4—Unverified
4GIUNetAccuracy95.7—Unverified
5G_InceptionAccuracy95—Unverified
6GICAccuracy94.44—Unverified
7CIN++Accuracy94.4—Unverified
8sGINAccuracy94.14—Unverified
9CANAccuracy94.1—Unverified
10Deep WL SGN(0,1,2)Accuracy93.68—Unverified
#ModelMetricClaimedVerifiedStatus
1TFGW ADJ (L=2)Accuracy88.1—Unverified
2WKPI-kmeansAccuracy87.2—Unverified
3FGW wl h=4 spAccuracy86.42—Unverified
4WL-OA KernelAccuracy86.1—Unverified
5WL-OAAccuracy86.1—Unverified
6FGW wl h=2 spAccuracy85.82—Unverified
7WWLAccuracy85.75—Unverified
8δ-2-LWLAccuracy85.5—Unverified
9DUGNNAccuracy85.5—Unverified
10CIN++Accuracy85.3—Unverified