Universidade Federal do Ceará
Mestrado e Doutorado em Ciências da Computação

Título: Sparse Gaussian Processes in Semi-Supervised Problems

Data: 18/06/2024
Horário: 14h00
Local: Google Meet (https://meet.google.com/dsa-oobt-ywd)

Resumo:

Labeling data samples can be challenging, expensive, and time-consuming. The lack of sufficient labeled data can make the application of supervised machine learning models impractical. Semi-supervised learning models have been extensively researched over the past decades. In this context, Gaussian Processes (GPs) offer the advantage of quantifying forecast uncertainties and providing significant modeling flexibility. However, like several Bayesian models, they cannot be directly applied to semi-supervised problems. This work proposes a GP-based approach which simultaneously trains an unsupervised GP latent variable model (GPLVM) and a supervised sparse GP model. The method leverages both labeled and unlabeled data to create a more effective final classifier. Additionally, the approach incorporates a neural network to reproduce the latent variables learned by the GPLVM component, which enables its use with unseen data. The introduced approach is evaluated on several datasets and demonstrates promising results.

Banca examinadora:

• Prof. Dr. César Lincoln Cavalcante Mattos (MDCC/UFC – Orientador)
• Prof. Dr. João Paulo do Vale Madeiro (MDCC/UFC)
• Prof. Dr. João Paulo Pordeus Gomes (UFC)