8 papers · 1 filter
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…
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…
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…
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…
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…
Finding Patterns in Ambiguity: Interpretable Stress Testing in the Decision~Boundary
Inês Gomes, Luís F. Teixeira, Jan N. van Rijn +4
The increasing use of deep learning across various domains highlights the importance of understanding the decision-making processes of these black-box models. Recent research focus…