Graphs are data structures proper to represent real-world objects and their relationships having been widely studied in theory and with multiple examples of applications in industries and academic research. Applying graph-based data in machine learning had a significant advance with the proposal of Graph Neural Networks (GNNs), allowing the representation of this type of data in algorithms that can retain features from the graph without the need for preprocessing stage. This master\'s dissertation presents an analysis of GNNs and proposes an application on text classification using topic modelling to create descriptive variables in bi-partite graphs.Grafos são estruturas de dados adequadas para representar objetos do mundo real e suas inter...
This article presents a bipartite graph propagation method to be applied to different tasks in the m...
In recent years, graph neural networks (GNN) have succeeded in many structural data analyses, includ...
Compared to sequential learning models, graph-based neural networks exhibit some excellent propertie...
Tratar grandes quantidades de dados é uma exigência dos modernos algoritmos de mineração de texto. P...
Orientador: Eduardo Jaques SpinosaDissertação (mestrado) - Universidade Federal do Paraná, Setor de ...
O grande volume de informação textual sendo gerado a todo momento torna necessário o aprimoramento c...
Diversas são as aplicações que podem ser expressas por meio de grafos [2]. Algoritmos [3] e modelos ...
The main topic of this doctoral dissertation is the extraction of valuable in- formation associate...
Deep learning (DL) has consistently pushed the state-of-the-art in many fields over the last years. ...
Sistemas complexos são compostos de diversos componentes que interagem entre si. Uma abordagem natur...
Applications such as electronic commerce, computer networks, social networks, and biology (protein i...
Submitted by Lúcia Brandão (lucia.elaine@live.com) on 2015-12-14T18:11:19Z No. of bitstreams: 1 Di...
Métodos baseados em grafos consistem em uma poderosa forma de representação e abstração de dados que...
This project will explore some of the most prominent Graph Neural Network variants and apply them to...
Topic classification of texts is one of the most interesting challenges in Natural Language Processi...
This article presents a bipartite graph propagation method to be applied to different tasks in the m...
In recent years, graph neural networks (GNN) have succeeded in many structural data analyses, includ...
Compared to sequential learning models, graph-based neural networks exhibit some excellent propertie...
Tratar grandes quantidades de dados é uma exigência dos modernos algoritmos de mineração de texto. P...
Orientador: Eduardo Jaques SpinosaDissertação (mestrado) - Universidade Federal do Paraná, Setor de ...
O grande volume de informação textual sendo gerado a todo momento torna necessário o aprimoramento c...
Diversas são as aplicações que podem ser expressas por meio de grafos [2]. Algoritmos [3] e modelos ...
The main topic of this doctoral dissertation is the extraction of valuable in- formation associate...
Deep learning (DL) has consistently pushed the state-of-the-art in many fields over the last years. ...
Sistemas complexos são compostos de diversos componentes que interagem entre si. Uma abordagem natur...
Applications such as electronic commerce, computer networks, social networks, and biology (protein i...
Submitted by Lúcia Brandão (lucia.elaine@live.com) on 2015-12-14T18:11:19Z No. of bitstreams: 1 Di...
Métodos baseados em grafos consistem em uma poderosa forma de representação e abstração de dados que...
This project will explore some of the most prominent Graph Neural Network variants and apply them to...
Topic classification of texts is one of the most interesting challenges in Natural Language Processi...
This article presents a bipartite graph propagation method to be applied to different tasks in the m...
In recent years, graph neural networks (GNN) have succeeded in many structural data analyses, includ...
Compared to sequential learning models, graph-based neural networks exhibit some excellent propertie...