A temporal extension of TabDDPM generates coherent synthetic time-series sequences on the WISDM dataset that match real distributions and support downstream classification with macro F1 of 0.64.
”Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees”.https://arxiv.org/abs/2309
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation
A temporal extension of TabDDPM generates coherent synthetic time-series sequences on the WISDM dataset that match real distributions and support downstream classification with macro F1 of 0.64.