id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-028688-5uzl1jpu	Li, Peisen	Multi-granularity Complex Network Representation Learning	2020-06-10		.txt	text/plain	4539	277	46	In this paper, we propose a multi-granularity complex network representation learning model (MNRL), which integrates topological structure and additional information at the same time, and presents these fused information learning into the same granularity semantic space that through fine-to-coarse to refine the complex network. A series of deep learning-based network representation methods were then proposed to further solve the problems of global topological structure preservation and high-order nonlinearity of data, and increased efficiency. So these location attributes and activity information are inherently indecomposable and interdependence with the suspect, making the two nodes recognize at a finer granularity based on the additional information and relationship structure that the low-dimensional representation vectors learned have certain similarities. To better characterize multiple granularity complex networks and solve the problem of nodes with potential associations that cannot be processed through the relationship structure alone, we refine the granularity to additional attributes, and designed an information fusion method, which are defined as follows:	./cache/cord-028688-5uzl1jpu.txt	./txt/cord-028688-5uzl1jpu.txt