Papers with Code · CC BY-SA 4.0
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.
<span style="color:grey; opacity: 0.6">( Image credit: Fast Graph Representation Learning With PyTorch Geometric )</span>
데이터셋
163개CoraCiteseerPubmedWisconsinActorTexasChameleonCornellSquirrelCiteSeer with Public Split: fixed 20 nodes per classChameleon (60%/20%/20% random splits)Film (60%/20%/20% random splits)PubMed (60%/20%/20% random splits)PubMed with Public Split: fixed 20 nodes per classSquirrel (60%/20%/20% random splits)Cora with Public Split: fixed 20 nodes per classCornell (60%/20%/20% random splits)Texas (60%/20%/20% random splits)Wisconsin (60%/20%/20% random splits)CiteSeer (60%/20%/20% random splits)Cora (60%/20%/20% random splits)Cornell (60%/20%/20% random splits)Chameleon(60%/20%/20% random splits)Penn94Texas(60%/20%/20% random splits)Wisconsin(60%/20%/20% random splits)Chameleon (48%/32%/20% fixed splits)Squirrel (48%/32%/20% fixed splits)Deezer-EuropePenn94