Graph Learning Network (GLN)

Please use this identifier to cite or link to this item: https://doi.org/10.25824/redu/B3XYDD

DOI:	https://doi.org/10.25824/redu/B3XYDD
Title:	Graph Learning Network (GLN)
Subject:	Computer and Information Science
Description:	GLN creates a set of node embeddings H(l) that are later combined to produce an intermediary representation H_int(l). Then, we use the updated node information with the adjacency information to produce a local embedding of the nodes' information H_local(l) that is also the output H(l+1). We also broadcast the information of the local embedding to produce a global embedding H_global(l). We combine the local and global embeddings to predict the next layer adjacency A(l+1). Additionally, we create three Synthetic Graph Datasets: the 3D-Surface, Community, and Geometric Figures. The source code is available in the public repository https://gitlab.com/mipl/graph-learning-network and the datasets are available in https://gitlab.com/mipl/graph-learning-network/-/tree/master/datasets.
Authors:	Saire Pilco, Darwin Danilo Ramirez Rivera, Gerberth Adin
URI:	https://doi.org/10.25824/redu/B3XYDD https://redu.unicamp.br/dataset.xhtml?persistentId=doi:10.25824/redu/B3XYDD
Other Identifiers:
Sponsorship:	Fundação de Amparo à Pesquisa do Estado de São Paulo
Sponsor ID:	FAPESP: 2017/16597-7
Rights:
Date:	1-Mar-2021
Available Data:
Format:
Type:
Publisher:	Saire Pilco, Darwin
Language :
Appears in Collections:	Repositório de Dados de Pesquisa da UNICAMP

Research data metasearch