SOTAVerified

Node Classification

Node Classification is a machine learning task in graph-based data analysis, where the goal is to assign labels to nodes in a graph based on the properties of nodes and the relationships between them.

Node Classification models aim to predict non-existing node properties (known as the target property) based on other node properties. Typical models used for node classification consists of a large family of graph neural networks. Model performance can be measured using benchmark datasets like Cora, Citeseer, and Pubmed, among others, typically using Accuracy and F1.

( Image credit: Fast Graph Representation Learning With PyTorch Geometric )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–200 of 1860 papers

TitleStatusHype
Heterophilic Graph Neural Networks Optimization with Causal Message-passing—0
Scalable Deep Metric Learning on Attributed Graphs—0
Contrast Similarity-Aware Dual-Pathway Mamba for Multivariate Time Series Node ClassificationCode0
Graph as a feature: improving node classification with non-neural graph-aware logistic regressionCode0
Higher Order Graph Attention Probabilistic Walk Networks—0
Towards Federated Graph Learning in One-shot Communication—0
Training a Label-Noise-Resistant GNN with Reduced ComplexityCode0
IMPaCT GNN: Imposing invariance with Message Passing in Chronological split Temporal Graphs—0
From Primes to Paths: Enabling Fast Multi-Relational Graph AnalysisCode0
ScaleNet: Scale Invariance Learning in Directed GraphsCode0
Shedding Light on Problems with Hyperbolic Graph Learning—0
Inductive Graph Few-shot Class Incremental Learning—0
An Efficient Memory Module for Graph Few-Shot Class-Incremental LearningCode0
HeteroSample: Meta-path Guided Sampling for Heterogeneous Graph Representation Learning—0
Post-Hoc Robustness Enhancement in Graph Neural Networks with Conditional Random Fields—0
YOSO: You-Only-Sample-Once via Compressed Sensing for Graph Neural Network Training—0
GaGSL: Global-augmented Graph Structure Learning via Graph Information Bottleneck—0
Higher-Order GNNs Meet Efficiency: Sparse Sobolev Graph Neural NetworksCode0
Enhancing the Expressivity of Temporal Graph Networks through Source-Target IdentificationCode0
Graph Neural Networks with Coarse- and Fine-Grained Division for Mitigating Label Sparsity and Noise—0
High-Pass Graph Convolutional Network for Enhanced Anomaly Detection: A Novel ApproachCode0
G-SPARC: SPectral ARchitectures tackling the Cold-start problem in Graph learning—0
RAGraph: A General Retrieval-Augmented Graph Learning FrameworkCode1
DeCaf: A Causal Decoupling Framework for OOD Generalization on Node Classification—0
Sparse Decomposition of Graph Neural Networks—0
Bonsai: Gradient-free Graph Condensation for Node Classification—0
SaVe-TAG: Semantic-aware Vicinal Risk Minimization for Long-Tailed Text-Attributed Graphs—0
Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node ClassificationCode0
LEX-GNN: Label-Exploring Graph Neural Network for Accurate Fraud DetectionCode0
LEGO-Learn: Label-Efficient Graph Open-Set LearningCode0
FIT-GNN: Faster Inference Time for GNNs Using CoarseningCode0
Improving Graph Neural Networks by Learning Continuous Edge DirectionsCode0
Learning to Control the Smoothness of Graph Convolutional Network Features—0
Multi-frame Detection via Graph Neural Networks: A Link Prediction Approach—0
Explanation-Preserving Augmentation for Semi-Supervised Graph Representation LearningCode2
Rethinking Graph Transformer Architecture Design for Node Classification—0
Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting ApproachCode1
LLM-Based Multi-Agent Systems are Scalable Graph Generative ModelsCode2
Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter TuningCode0
FedGraph: A Research Library and Benchmark for Federated Graph LearningCode2
Improving Node Representation by Boosting Target-Aware Contrastive Loss—0
How to Make LLMs Strong Node Classifiers?—0
Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic TransformsCode0
ClassContrast: Bridging the Spatial and Contextual Gaps for Node Representations—0
DuoGNN: Topology-aware Graph Neural Network with Homophily and Heterophily Interaction-DecouplingCode0
Conformal Prediction: A Theoretical Note and Benchmarking Transductive Node Classification in GraphsCode0
On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks—0
Convolutional Signal Propagation: A Simple Scalable Algorithm for Hypergraphs—0
GISExplainer: On Explainability of Graph Neural Networks via Game-theoretic Interaction Subgraphs—0
Preventing Representational Rank Collapse in MPNNs by Splitting the Computational GraphCode0
Show:102550
← PrevPage 4 of 38Next →
All datasetsCiteseerPubmedCoraCiteSeer with Public Split: fixed 20 nodes per classPubMed with Public Split: fixed 20 nodes per classCora with Public Split: fixed 20 nodes per classPPICoauthor CSCora (0.5%)Cora (1%)Cora (3%)PubMed (0.03%)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NodeNetAccuracy80.09—Unverified
2SplineCNNAccuracy79.2—Unverified
3PathNetAccuracy (%)77.98—Unverified
43ferenceAccuracy76.33—Unverified
5MMAAccuracy76.3—Unverified
6PPNPAccuracy75.83—Unverified
7CoLinkDistAccuracy75.79—Unverified
8CoLinkDistMLPAccuracy75.77—Unverified
9APPNPAccuracy75.73—Unverified
10CleoraAccuracy75.7—Unverified
#ModelMetricClaimedVerifiedStatus
1NodeNetAccuracy90.21—Unverified
2CoLinkDistAccuracy89.58—Unverified
3CoLinkDistMLPAccuracy89.53—Unverified
4PathNetAccuracy (%)88.92—Unverified
53ferenceAccuracy88.9—Unverified
6SplineCNNAccuracy88.88—Unverified
7LinkDistAccuracy88.86—Unverified
8LinkDistMLPAccuracy88.79—Unverified
9PairEF188.57—Unverified
10GCN + MixupAccuracy87.9—Unverified
#ModelMetricClaimedVerifiedStatus
1LinkDistAccuracy88.24—Unverified
2CoLinkDistAccuracy87.89—Unverified
33ferenceAccuracy87.78—Unverified
4LinkDistMLPAccuracy87.58—Unverified
5CoLinkDistMLPAccuracy87.54—Unverified
6CleoraAccuracy86.8—Unverified
7NodeNetAccuracy86.8—Unverified
8MMAAccuracy85.8—Unverified
9GResNet(GAT)Accuracy85.5—Unverified
10TransGNN1:1 Accuracy85.1—Unverified
#ModelMetricClaimedVerifiedStatus
1OGCAccuracy77.5—Unverified
2LDS-GNNAccuracy75—Unverified
3CPF-tra-APPNPAccuracy74.6—Unverified
4G3NNAccuracy74.5—Unverified
5GGCMAccuracy74.2—Unverified
6GEMAccuracy74.2—Unverified
7Truncated KrylovAccuracy73.86—Unverified
8SSGCAccuracy73.6—Unverified
9OKDEEMAccuracy73.53—Unverified
10GCNIIAccuracy73.4—Unverified
#ModelMetricClaimedVerifiedStatus
1OGCAccuracy83.4—Unverified
2CPF-tra-GCNIIAccuracy83.2—Unverified
3DSGCNAccuracy81.9—Unverified
4Truncated KrylovAccuracy81.7—Unverified
5SuperGAT MXAccuracy81.7—Unverified
6G-APPNPAccuracy80.95—Unverified
7GGCMAccuracy80.8—Unverified
8GCN(predicted-targets)Accuracy80.42—Unverified
9SSGCAccuracy80.4—Unverified
10GCNIIAccuracy80.2—Unverified
#ModelMetricClaimedVerifiedStatus
1OGCAccuracy86.9—Unverified
2GCN-TVAccuracy86.3—Unverified
3GCNIIAccuracy85.5—Unverified
4CPF-ind-APPNPAccuracy85.3—Unverified
5AIR-GCNAccuracy84.7—Unverified
6H-GCNAccuracy84.5—Unverified
7G-APPNPAccuracy84.31—Unverified
8SuperGAT MXAccuracy84.3—Unverified
9DSGCNAccuracy84.2—Unverified
10LDS-GNNAccuracy84.1—Unverified