id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
bandyopadhyay-beyond-2021			2019-12-12	8	.pdf	application/pdf	8115	689	68	Towards this end, we propose a novel concept of converting a network to its weighted line graph which is ideally suited to find the embedding of edges of the original network. unsupervised approach for edge embedding in homogeneous information networks, without relying on the node embeddings. Our proposed optimization framework for edge embedding also generates a set of node embeddings, which are not just the aggregation • We propose a novel edge embedding framework line2vec, for homogeneous social and information networks. different types of edges in a heterogeneous network, but their proposed method essentially uses an aggregation function inside the optimization framework to generate edge embeddings from the node nodes of the line graph, which essentially provides the edge embeddings of the original network. embedding of the node vuv in line graph (or the edge (u,v) ∈ E). Also two edges having similar neighborhood in the original network lead to two nodes having similar neighborhood in the transformed line graph.	./cache/bandyopadhyay-beyond-2021.pdf	./txt/bandyopadhyay-beyond-2021.txt