node2vec: Scalable Feature Learning for Networks

node2vec : Scalable Feature Learning for NetworksAditya GroverStanford LeskovecStanford tasks over nodes and edges in Networks require carefuleffort in engineering features used by Learning algorithms. Recentresearch in the broader field of representation Learning has led tosignificant progress in automating prediction by Learning the fea-tures themselves. However, present Feature Learning approachesare not expressive enough to capture the diversity of connectivitypatterns observed in we proposenode2vec, an algorithmic framework for learn-ing continuous Feature representations for nodes in Networks . Innode2vec, we learn a mapping of nodes to a low-dimensional spaceof features that maximizes the likelihood of preserving networkneighborhoods of nodes. We define a flexible notion of a node snetwork neighborhood and design a biased random walk procedure,which efficiently explores diverse neighborhoods. Our algorithmgeneralizes prior work which is based on rigid notions of networkneighborhoods, and we argue that the added flexibility in exploringneighborhoods is the key to Learning richer demonstrate the efficacy ofnode2vecover existing state-of-the-art techniques on multi-label classification and link predictionin several real-world Networks from diverse domains.

feature extraction techniques which typically involve some seed hand-crafted features based on network properties [8, 11]. In con-trast, our goal is to automate the whole process by casting feature extraction as a representation learning problem in which case we do not require any hand-engineered features.

Loading..

Tags:

  Extraction, Node2vec

Information

Related search queries