2 papers
cs.LG2018
Semi-Supervised Learning on Graphs Based on Local Label Distributions
Evgeniy Faerman, Felix Borutta, Julian Busch +1
Most approaches that tackle the problem of node classification consider nodes to be similar, if they have shared neighbors or are close to each other in the graph. Recent methods f…
cs.SI2017
LASAGNE: Locality And Structure Aware Graph Node Embedding
Evgeniy Faerman, Felix Borutta, Kimon Fountoulakis +1
In this work we propose Lasagne, a methodology to learn locality and structure aware graph node embeddings in an unsupervised way. In particular, we show that the performance of ex…