Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Unsupervised and Scalable Algorithm for Learning Node Representations
Tiago Pimentel, Adriano Veloso, Nivio Ziviani
Feb 17, 2017 (modified: Mar 22, 2017)ICLR 2017 workshop submissionreaders: everyone
Abstract:Representation learning is one of the foundations of Deep Learning and allowed big improvements on several Machine Learning fields, such as Neural Machine Translation, Question Answering and Speech Recognition. Recent works have proposed new methods for learning representations for nodes and edges in graphs. In this work, we propose a new unsupervised and efficient method, called here Neighborhood Based Node Embeddings (NBNE), capable of generating node embeddings for very large graphs. This method is based on SkipGram and uses nodes' neighborhoods as contexts to generate representations. NBNE achieves results comparable or better to the state-of-the-art in three different datasets.
TL;DR:An unsupervised and efficient method capable of generating node embeddings for very large graphs.
Enter your feedback below and we'll get back to you as soon as possible.