Graph Rewiring
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/135407
Título: | Graph Rewiring |
---|---|
Autor/es: | Begga, Ahmed |
Director de la investigación: | Escolano, Francisco |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial |
Palabras clave: | Deep Learning | Graph Neural Networks | Heterophily | Graph Rewiring | Spectral Theory | Attention Mechanisms | Structural Encoding | PyTorch |
Fecha de publicación: | 23-jun-2023 |
Fecha de lectura: | 20-jun-2023 |
Resumen: | Neural networks have proven to be a powerful tool for solving a wide range of problems in areas such as computer vision, natural language processing, and machine learning in general. However, most neural network architectures have been developed to work with vectorized data such as images and sequences, eluding the treatment of data such as graphs or point clouds. Graphs are ideal for modeling complex relationships between entities. Many applications rely on graphs, such as social networks, product recommendations, or bioinformatics. Due to the non-vectorial nature of graphs, their processing presents unique and challenging problems in machine learning. In recent years, there has been a growing trend in deep learning techniques for graphs. These techniques use neural networks to process graphs directly, using vector (latent) representations of nodes and edges. This leads to an emerging field of research known as Graph Neural Networks. Throughout this Master’s Thesis, we will explore the most common architectures for Graph Neural Networks and the problems that these architectures face, mainly the over-smoothing issue. Finally, we will propose a new metric and method based on Spectral Graph Theory, Dirichlet energies and Graph Rewiring to achieve competitive results in semi-supervised node classification. |
URI: | http://hdl.handle.net/10045/135407 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/masterThesis |
Derechos: | Licencia Creative Commons Reconocimiento-NoComercial-SinObraDerivada 4.0 |
Aparece en las colecciones: | Máster Universitario en Ciencia de Datos - Trabajos Fin de Máster |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Graph_Rewiring_Begga_Hachlafi_Ahmed.pdf | 10,25 MB | Adobe PDF | Abrir Vista previa | |
Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.