metapath2vec: Scalable Representation Learning for ...
Metapath2vec: Scalable Representation Learning forHeterogeneous NetworksYuxiao Dong Microso ResearchRedmond, WA 98052yuxdong@microso .comNitesh V. ChawlaUniversity of Notre DameNotre Dame, IN SwamiArmy Research LaboratoryAdelphi, MD study the problem of Representation Learning in heterogeneousnetworks. Its unique challenges come from the existence of mul-tiple types of nodes and links, which limit the feasibility of theconventional network embedding techniques. We develop twoscalable Representation Learning models, namelymetapath2vecandmetapath2vec++. emetapath2vecmodel formalizes meta-path-based random walks to construct the heterogeneous neighborhoodof a node and then leverages a heterogeneous skip-gram modelto perform node embeddings. emetapath2vec++model furtherenables the simultaneous modeling of structural and semantic cor-relations in heterogeneous networks.
also di‡er from the Predictive Text Embedding (PTE) model [29] in several ways. First, PTE is a semi-supervised learning model that incorporates label information for text data. Second, the het-erogeneity in PTE comes from the text network wherein a link connects two words, a word and its document, and a word and its label.
Download metapath2vec: Scalable Representation Learning for ...
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: