activity
20242026
collaborators

7 papers

cs.LG2026

Benchmarking Time Series Generation Methods for Privacy-Preserving Forecasting

Luis Amorim, Vitor Cerqueira, Moises Santos +2

Time series forecasting in privacy-sensitive domains often requires training models on released data rather than original observations. Synthetic time series generation has been de…

cs.LG2026

Rashomon Alignment

Moisés Santos, Peter van der Putten, Bernhard Pfahringer +1

We propose Rashomon Alignment (RA), a new measure to assess functional similarity between two models. Existing functional similarity measures are distributional, quantifying differ…

cs.LG2026

Exploring Transformer Placement in Variational Autoencoders for Tabular Data Generation

Aníbal Silva, Moisés Santos, André Restivo +1

Tabular data remains a challenging domain for generative models. In particular, the standard Variational Autoencoder (VAE) architecture, typically composed of multilayer perceptron…

cs.LG2026

Grasynda: Graph-based Synthetic Time Series Generation

Luis Amorim, Moises Santos, Paulo J. Azevedo +2

Data augmentation is a crucial tool in time series forecasting, especially for deep learning architectures that require a large training sample size to generalize effectively. Howe…

cs.LG2025

Online Data Augmentation for Forecasting with Deep Learning

Vitor Cerqueira, Moisés Santos, Luis Roque +2

Deep learning approaches are increasingly used to tackle forecasting tasks involving datasets with multiple univariate time series. A key factor in the successful application of th…

cs.LG2024

Tabular data generation with tensor contraction layers and transformers

Aníbal Silva, André Restivo, Moisés Santos +1

Generative modeling for tabular data has recently gained significant attention in the Deep Learning domain. Its objective is to estimate the underlying distribution of the data. Ho…