US 12743607 B1 / Sep 22, 2026

System and method for generating synthetic data with masked transformers

A transformer-based modeling architecture for training a generator to generate synthetic data. The architecture includes embedding models for embedding input data having multiple fields containing real data values and constructing individual embedding matrices for each of the multiple fields, a masking model for producing a set of masked fields in the embedded input dataset and replacing the real data value of each field with a mask token; and a transformer model for predicting the real data value for each mask token in each of the masked fields over multiple iterations.