Node Classification

769 papers with code • 122 benchmarks • 68 datasets

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 )

Libraries

Use these libraries to find Node Classification models and implementations

Most implemented papers

Hierarchical Graph Representation Learning with Differentiable Pooling

dmlc/dgl NeurIPS 2018

Recently, graph neural networks (GNNs) have revolutionized the field of graph representation learning through effectively learned node embeddings, and achieved state-of-the-art results in tasks such as node classification and link prediction.

Gated Graph Sequence Neural Networks

dmlc/dgl 17 Nov 2015

Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases.

Deep Graph Infomax

PetarV-/DGI ICLR 2019

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner.

LINE: Large-scale Information Network Embedding

tangjianpku/LINE 12 Mar 2015

This paper studies the problem of embedding very large information networks into low-dimensional vector spaces, which is useful in many tasks such as visualization, node classification, and link prediction.

Convolutional Networks on Graphs for Learning Molecular Fingerprints

HIPS/neural-fingerprint NeurIPS 2015

We introduce a convolutional neural network that operates directly on graphs.

EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

IBM/EvolveGCN 26 Feb 2019

Existing approaches typically resort to node embeddings and use a recurrent neural network (RNN, broadly speaking) to regulate the embeddings and learn the temporal dynamics.

Principal Neighbourhood Aggregation for Graph Nets

lukecavabarrett/pna NeurIPS 2020

Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data.

Simplifying Graph Convolutional Networks

Tiiiger/SGC 19 Feb 2019

Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations.

GraphSAINT: Graph Sampling Based Inductive Learning Method

GraphSAINT/GraphSAINT ICLR 2020

Graph Convolutional Networks (GCNs) are powerful models for learning representations of attributed graphs.

DropEdge: Towards Deep Graph Convolutional Networks on Node Classification

DropEdge/DropEdge ICLR 2020

\emph{Over-fitting} and \emph{over-smoothing} are two main obstacles of developing deep Graph Convolutional Networks (GCNs) for node classification.