Two new evaluation metrics, a network-graph similarity score and a holdout-based privacy ratio, reveal that current tabular generative models fall short on NYC taxi trip data.
In: NeurIPS 2023 Workshop on Synthetic Data Generation with Generative AI (2023) 7
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Systematic Evaluation of Generative Models on Tabular Transportation Data
Two new evaluation metrics, a network-graph similarity score and a holdout-based privacy ratio, reveal that current tabular generative models fall short on NYC taxi trip data.