About

The node classification task is one where the algorithm has to determine the labelling of samples (represented as nodes) by looking at the labels of their neighbours.

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

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Datasets

Latest papers with code

CrossWalk: Fairness-enhanced Node Representation Learning

6 May 2021ahmadkhajehnejad/CrossWalk

The potential for machine learning systems to amplify social inequities and unfairness is receiving increasing popular and academic attention.

FAIRNESS LINK PREDICTION NODE CLASSIFICATION REPRESENTATION LEARNING

0
06 May 2021

Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks

16 Apr 2021safe-graph/RioGNN

A reinforced relation-aware neighbor selection mechanism is developed to choose the most similar neighbors of a targeting node within a relation before aggregating all neighborhood information from different relations to obtain the eventual node embedding.

NODE CLASSIFICATION REPRESENTATION LEARNING

1
16 Apr 2021

Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks

16 Apr 2021RingBDStack/HAE

Furthermore, they cannot fully capture the content-based correlations between nodes, as they either do not use the self-attention mechanism or only use it to consider the immediate neighbors of each node, ignoring the higher-order neighbors.

NODE CLASSIFICATION NODE CLUSTERING REPRESENTATION LEARNING

0
16 Apr 2021

mSHINE: A Multiple-meta-paths Simultaneous Learning Framework for Heterogeneous Information Network Embedding

6 Apr 2021XinyiZ001/mSHINE

To address this issue, a novel meta-path-based HIN representation learning framework named mSHINE is designed to simultaneously learn multiple node representations for different meta-paths.

LINK PREDICTION NETWORK EMBEDDING NODE CLASSIFICATION

2
06 Apr 2021

OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs

17 Mar 2021snap-stanford/ogb

We show that the expressive models significantly outperform simple scalable baselines, indicating an opportunity for dedicated efforts to further improve graph ML at scale.

GRAPH LEARNING GRAPH REGRESSION KNOWLEDGE GRAPHS LINK PREDICTION NODE CLASSIFICATION

926
17 Mar 2021

GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks

16 Mar 2021TianxiangZhao/GraphSmote

This task is non-trivial, as previous synthetic minority over-sampling algorithms fail to provide relation information for newly synthesized samples, which is vital for learning on graphs.

CLASSIFICATION GRAPH LEARNING NODE CLASSIFICATION

16
16 Mar 2021

Nishimori meets Bethe: a spectral method for node classification in sparse weighted graphs

5 Mar 2021lorenzodallamico/NishimoriBetheHessian

This article unveils a new relation between the Nishimori temperature parametrizing a distribution P and the Bethe free energy on random Erdos-Renyi graphs with edge weights distributed according to P. Estimating the Nishimori temperature being a task of major importance in Bayesian inference problems, as a practical corollary of this new relation, a numerical method is proposed to accurately estimate the Nishimori temperature from the eigenvalues of the Bethe Hessian matrix of the weighted graph.

BAYESIAN INFERENCE CLASSIFICATION NODE CLASSIFICATION

1
05 Mar 2021

CogDL: An Extensive Toolkit for Deep Learning on Graphs

1 Mar 2021THUDM/cogdl

Most of the graph embedding methods learn node-level or graph-level representations in an unsupervised way and preserves the graph properties such as structural information, while graph neural networks capture node features and work in semi-supervised or self-supervised settings.

GRAPH CLASSIFICATION GRAPH EMBEDDING GRAPH REPRESENTATION LEARNING LINK PREDICTION NODE CLASSIFICATION RECOMMENDATION SYSTEMS

655
01 Mar 2021

MagNet: A Magnetic Neural Network for Directed Graphs

22 Feb 2021hazdzz/MagNet

In this paper, we propose MagNet, a spectral GNN for directed graphs based on a complex Hermitian matrix known as the magnetic Laplacian.

LINK PREDICTION NODE CLASSIFICATION

0
22 Feb 2021

A Deep Graph Wavelet Convolutional Neural Network for Semi-supervised Node Classification

19 Feb 2021qncsn2016/DeepGWC

Graph convolutional neural network provides good solutions for node classification and other tasks with non-Euclidean data.

CLASSIFICATION NODE CLASSIFICATION

2
19 Feb 2021