node2vec: Scalable Feature Learning for Networks

3 Jul 2016Aditya GroverJure Leskovec

Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progress in automating prediction by learning the features themselves... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Node Classification BlogCatalog node2vec Accuracy 21.50% # 4
Node Classification BlogCatalog node2vec Macro-F1 0.206 # 5
Node Classification Wikipedia node2vec Accuracy 19.10% # 4
Node Classification Wikipedia node2vec Macro-F1 0.179 # 4