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

Showing 17511800 of 1860 papers

TitleStatusHype
LanczosNet: Multi-Scale Deep Graph Convolutional NetworksCode0
Graph Neural Networks with convolutional ARMA filtersCode0
Dynamic Graph Representation Learning via Self-Attention NetworksCode0
Graph Node-Feature Convolution for Representation LearningCode0
Enhanced Network Embedding with Text InformationCode0
Attributed Network Embedding for Incomplete Attributed NetworksCode0
Node Embedding with Adaptive Similarities for Scalable Learning over GraphsCode0
DynamicGEM: A Library for Dynamic Graph Embedding MethodsCode0
Spectral Multigraph Networks for Discovering and Fusing Relationships in MoleculesCode0
MGCN: Semi-supervised Classification in Multi-layer Graphs with Graph Convolutional NetworksCode0
Role action embeddings: scalable representation of network positionsCode0
Pitfalls of Graph Neural Network EvaluationCode0
Multi-Task Graph AutoencodersCode0
Towards Sparse Hierarchical Graph ClassifiersCode0
Accurate, Efficient and Scalable Graph EmbeddingCode0
Streaming Graph Neural NetworksCode1
Deep Autoencoder-like Nonnegative Matrix Factorization for Community DetectionCode0
Binarized Attributed Network EmbeddingCode0
Node Representation Learning for Directed Graphs0
TNE: A Latent Model for Representation Learning on Networks0
Predict then Propagate: Graph Neural Networks meet Personalized PageRankCode0
Attention Models with Random Features for Multi-layered Graph Embeddings0
How Powerful are Graph Neural Networks?Code1
Graph U-Net0
Deep Graph InfomaxCode1
Universal Network Representation for Heterogeneous Information Networks0
Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised LearningCode0
Improved Deep Embeddings for Inferencing with Multi-Layered Networks0
Adaptive Sampling Towards Fast Graph Representation LearningCode0
Higher-order Graph Convolutional Networks0
Node Classification for Signed Social Networks Using Diffuse Interface MethodsCode0
Exploiting Edge Features in Graph Neural Networks0
Learning Embeddings of Directed Networks with Text-Associated Nodes---with Applications in Software Package Dependency Networks0
Deep Feature Learning of Multi-Network Topology for Node Classification0
BiasedWalk: Biased Sampling for Representation Learning on GraphsCode0
Large-Scale Learnable Graph Convolutional NetworksCode0
Empirical Risk Minimization and Stochastic Gradient Descent for Relational DataCode0
Hierarchical Graph Representation Learning with Differentiable PoolingCode1
Representation Learning on Graphs with Jumping Knowledge NetworksCode0
Spectral Network Embedding: A Fast and Scalable Method via Sparsity0
Fusion Graph Convolutional NetworksCode0
Adversarial Attacks on Neural Networks for Graph DataCode0
Diffusion Based Network Embedding0
Billion-scale Network Embedding with Iterative Random ProjectionCode0
RECS: Robust Graph Embedding Using Connection Subgraphs0
t-PINE: Tensor-based Predictable and Interpretable Node Embeddings0
Neural-Brane: Neural Bayesian Personalized Ranking for Attributed Network EmbeddingCode0
Graph Convolutional Neural Networks via ScatteringCode0
Graphite: Iterative Generative Modeling of GraphsCode0
Fast Sequence Based Embedding with Diffusion GraphsCode1
Show:102550
← PrevPage 36 of 38Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NodeNetAccuracy80.09Unverified
2SplineCNNAccuracy79.2Unverified
3PathNetAccuracy (%)77.98Unverified
43ferenceAccuracy76.33Unverified
5MMAAccuracy76.3Unverified
6PPNPAccuracy75.83Unverified
7CoLinkDistAccuracy75.79Unverified
8CoLinkDistMLPAccuracy75.77Unverified
9APPNPAccuracy75.73Unverified
10CleoraAccuracy75.7Unverified
#ModelMetricClaimedVerifiedStatus
1NodeNetAccuracy90.21Unverified
2CoLinkDistAccuracy89.58Unverified
3CoLinkDistMLPAccuracy89.53Unverified
4PathNetAccuracy (%)88.92Unverified
53ferenceAccuracy88.9Unverified
6SplineCNNAccuracy88.88Unverified
7LinkDistAccuracy88.86Unverified
8LinkDistMLPAccuracy88.79Unverified
9PairEF188.57Unverified
10GCN + MixupAccuracy87.9Unverified
#ModelMetricClaimedVerifiedStatus
1LinkDistAccuracy88.24Unverified
2CoLinkDistAccuracy87.89Unverified
33ferenceAccuracy87.78Unverified
4LinkDistMLPAccuracy87.58Unverified
5CoLinkDistMLPAccuracy87.54Unverified
6NodeNetAccuracy86.8Unverified
7CleoraAccuracy86.8Unverified
8MMAAccuracy85.8Unverified
9GResNet(GAT)Accuracy85.5Unverified
10TransGNN1:1 Accuracy85.1Unverified
#ModelMetricClaimedVerifiedStatus
1OGCAccuracy77.5Unverified
2LDS-GNNAccuracy75Unverified
3CPF-tra-APPNPAccuracy74.6Unverified
4G3NNAccuracy74.5Unverified
5GEMAccuracy74.2Unverified
6GGCMAccuracy74.2Unverified
7Truncated KrylovAccuracy73.86Unverified
8SSGCAccuracy73.6Unverified
9OKDEEMAccuracy73.53Unverified
10GCNIIAccuracy73.4Unverified
#ModelMetricClaimedVerifiedStatus
1OGCAccuracy83.4Unverified
2CPF-tra-GCNIIAccuracy83.2Unverified
3DSGCNAccuracy81.9Unverified
4Truncated KrylovAccuracy81.7Unverified
5SuperGAT MXAccuracy81.7Unverified
6G-APPNPAccuracy80.95Unverified
7GGCMAccuracy80.8Unverified
8GCN(predicted-targets)Accuracy80.42Unverified
9SSGCAccuracy80.4Unverified
10GCNIIAccuracy80.2Unverified
#ModelMetricClaimedVerifiedStatus
1OGCAccuracy86.9Unverified
2GCN-TVAccuracy86.3Unverified
3GCNIIAccuracy85.5Unverified
4CPF-ind-APPNPAccuracy85.3Unverified
5AIR-GCNAccuracy84.7Unverified
6H-GCNAccuracy84.5Unverified
7G-APPNPAccuracy84.31Unverified
8SuperGAT MXAccuracy84.3Unverified
9DSGCNAccuracy84.2Unverified
10LDS-GNNAccuracy84.1Unverified