IIIT Hyderabad Publications
Author2Vec: Learning Author Representations by Combining Content and Link Information
Authors: Ganesh J,Soumyajit Ganguly,Manish Gupta,Vasudeva Varma,Vikram Pudi
Location Pisa, Italy.
Report no: IIIT/TR/2016/10
n this paper, we consider the problem of learning representations for authors from bibliographic co-authorship networks. Existing methods for deep learning on graphs, suchas DeepWalk, su er from link sparsity problem as they focus on modeling the link information only. We hypothesize that capturing both the content and link information in a uni edway will help mitigate the sparsity problem. To this end, we present a novel model `Author2Vec'1 , which learns lowdimensional author representations such that authors who write similar content and share similar network structure are closer in vector space. Such embeddings are useful in a variety of applications such as link prediction, node classi cation, recommendation and visualization. The author embeddings we learn are empirically shown to outperform DeepWalk by 2.35% and 0.83% for link prediction and clustering task respectively.
Full paper: pdf
Centre for Search and Information Extraction Lab
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved.