id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_zjh4gwjbrfbs3m2w5jy3as4kdu	Jisung Yoon	Persona2vec: a flexible multi-role representations learning framework for graphs	2021	20	.pdf	application/pdf	8908	1205	62	persona2vec, a graph embedding framework that efficiently learns multiple Keywords Graph embedding, Overlapping community, Social context, Social network analysis, persona2vec creates a persona graph, where some nodes are split into multiple personas. algorithm, node C in the original graph belongs to two non-overlapping clusters {A,B} node A only belongs to one ego cluster {B,C}, so it does not split into multiple personas. Any graph clustering algorithm can be employed for splitting a node into personas. common embedding methods could not be directly applied to the splitted graph. In the persona graph, we set the weights of the unweighted original edges as 1 and embedding where each persona node has its own vector representation. fine-tune the embedding vectors with the information from the persona graph (see Fig. 1). Our method for generating persona node embeddings. Persona2vec: a flexible multi-role representations learning framework for graphs Persona2vec: a flexible multi-role representations learning framework for graphs	./cache/work_zjh4gwjbrfbs3m2w5jy3as4kdu.pdf	./txt/work_zjh4gwjbrfbs3m2w5jy3as4kdu.txt