Data model generation using generative adversarial networks

Abstract

Methods for generating data models using a generative adversarial network can begin by receiving a data model generation request by a model optimizer from an interface. The model optimizer can provision computing resources with a data model. As a further step, a synthetic dataset for training the data model can be generated using a generative network of a generative adversarial network, the generative network trained to generate output data differing at least a predetermined amount from a reference dataset according to a similarity metric. The computing resources can train the data model using the synthetic dataset. The model optimizer can evaluate performance criteria of the data model and, based on the evaluation of the performance criteria of the data model, store the data model and metadata of the data model in a model storage. The data model can then be used to process production data.

1 - 20 . (canceled) 
     
     
         21 . A method for generating data models, comprising:
 receiving, by a model optimizer from an interface, a data model generation request;   provisioning, by the model optimizer, computing resources with a data model;   generating, by a dataset generator, a synthetic dataset for training the data model using a generative network, wherein the generative network comprises a decoder network configured to generate decoder output data in a sample space having a first dimensionality from decoder input data in a code space;   training, by the computing resources, the data model using the synthetic dataset; and   processing production data using the data model.   
     
     
         22 . The method of  claim 21 , wherein the generative network is trained to generate the output data with an output data schema matching a schema of a reference dataset. 
     
     
         23 . The method of  claim 22 , wherein the model optimizer is configured to generate at least one of a statistical correlation score between the synthetic dataset and the reference dataset, a data similarity score between the synthetic dataset and the reference dataset, or a data quality score for the synthetic dataset. 
     
     
         24 . The method of  claim 23 , wherein training the data model using the synthetic dataset comprises determining that the synthetic dataset satisfies a criterion concerning the at least one of the statistical correlation score between the synthetic dataset and the reference dataset, the data similarity score between the synthetic dataset and the reference dataset, or the data quality score for the synthetic dataset. 
     
     
         25 . The method of  claim 21 , wherein the decoder input data in the code space has a second dimensionality less than the first dimensionality. 
     
     
         26 . The method of  claim 21 , wherein generating the synthetic dataset for training the data model comprises:
 identifying a first point and a second point in the sample space, and   generating a first representative point and a second representative point in the code space using the first point, the second point, and an encoder network corresponding to the decoder network.   
     
     
         27 . The method of  claim 26 , wherein the first representative point is a centroid or a medoid of the first point and the second point. 
     
     
         28 . A system for generating data models, comprising:
 at least one processor; and   at least one non-transitory memory storing instructions that, when executed by the at least one processor cause a cloud computing system to perform operations comprising:
 receiving, by a model optimizer from an interface, a data model generation request; 
 provisioning, by the model optimizer, computing resources with a data model; 
 generating, by a dataset generator, a synthetic dataset for training the data model using a generative network, wherein the generative network comprises a decoder network configured to generate decoder output data in a sample space having a first dimensionality from decoder input data in a code space; 
 training, by the computing resources, the data model using the synthetic dataset; and 
 processing production data using the data model. 
   
     
     
         29 . The system of  claim 28 , wherein the generative network is trained to generate the output data with an output data schema matching a schema of a reference dataset. 
     
     
         30 . The system of  claim 29 , wherein the model optimizer is configured to generate at least one of a statistical correlation score between the synthetic dataset and the reference dataset, a data similarity score between the synthetic dataset and the reference dataset, and a data quality score for the synthetic dataset. 
     
     
         31 . The system of  claim 30 , wherein training the data model using the synthetic dataset comprises determining that the synthetic dataset satisfies a criterion concerning the at least one of the statistical correlation score between the synthetic dataset and the reference dataset, the data similarity score between the synthetic dataset and the reference dataset, and the data quality score for the synthetic dataset. 
     
     
         32 . The system of  claim 28 , wherein the decoder input data in the code space has a second dimensionality less than the first dimensionality. 
     
     
         33 . The system of  claim 28 , wherein generating the synthetic dataset for training the data model comprises:
 identifying a first point and a second point in the sample space, and   generating a first representative point and a second representative point in the code space using the first point, the second point, and an encoder network corresponding to the decoder network.   
     
     
         34 . The system of  claim 33 , wherein the first representative point is a centroid or a medoid of the first point and the second point. 
     
     
         35 . A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
 receiving, by a model optimizer from an interface, a data model generation request;   provisioning, by the model optimizer, computing resources with a data model;   generating, by a dataset generator, a synthetic dataset for training the data model using a generative network, wherein the generative network comprises a decoder network configured to generate decoder output data in a sample space having a first dimensionality from decoder input data in a code space;   training, by the computing resources, the data model using the synthetic dataset; and   processing production data using the data model.   
     
     
         36 . The computer-readable medium of  claim 35 , wherein the generative network is trained to generate the output data with an output data schema matching a schema of a reference dataset. 
     
     
         37 . The computer-readable medium of  claim 36 , wherein the model optimizer is configured to generate at least one of a statistical correlation score between the synthetic dataset and the reference dataset, a data similarity score between the synthetic dataset and the reference dataset, or a data quality score for the synthetic dataset. 
     
     
         38 . The computer-readable medium of  claim 37 , wherein training the data model using the synthetic dataset comprises determining that the synthetic dataset satisfies a criterion concerning the at least one of the statistical correlation score between the synthetic dataset and the reference dataset, the data similarity score between the synthetic dataset and the reference dataset, or the data quality score for the synthetic dataset. 
     
     
         39 . The computer-readable medium of  claim 35 , wherein generating the synthetic dataset for training the data model comprises:
 identifying a first point and a second point in the sample space, and   generating a first representative point and a second representative point in the code space using the first point, the second point, and an encoder network corresponding to the decoder network;   further wherein the first representative point is a medoid or a centroid of the first point and the second point.   
     
     
         40 . The computer-readable medium of  claim 35 , wherein the decoder input data in the code space has a second dimensionality less than the first dimensionality.