Patents by Inventor Kush Raj Varshney

Kush Raj Varshney has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12061640
    Abstract: Techniques facilitating using flow graphs to represent a data analysis program in a cloud based system for open science collaboration and discovery are provided. In an example, a system can represent a data analysis execution as a flow graph where vertices of the flow graph represent function calls made during the data analysis program and edges between the vertices represent objects passed between the functions. In another example, the flow graph can then be annotated using an annotation database to label the recognized function calls and objects. In another example, the system can then semantically label the annotated flow graph by aligning the annotated graph with a knowledge base of data analysis concepts to provide context for the operations being performed by the data analysis program.
    Type: Grant
    Filed: December 29, 2020
    Date of Patent: August 13, 2024
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Ioana Monica Baldini Soares, Aleksandra Mojsilovic, Evan J. Patterson, Kush Raj Varshney
  • Publication number: 20240135238
    Abstract: One or more systems, devices, computer program products and/or computer implemented methods of use provided herein relate to a process of mitigating biased training instances associated with a machine learning model without additional refitting of the machine learning model. A system can comprise a memory that stores computer executable components, and a processor that executed the computer executable components stored in the memory, wherein the computer executable components can comprise a training data influence estimation component and an influence mitigation component. The training data influence estimation component can receive a pre-trained machine learning model and calculate a fairness influence score of training instances on group fairness metrics associated with the pre-trained machine learning model.
    Type: Application
    Filed: October 10, 2022
    Publication date: April 25, 2024
    Inventors: Prasanna Sattigeri, Soumya Ghosh, Inkit Padhi, Pierre L. Dognin, Kush Raj Varshney
  • Publication number: 20240095575
    Abstract: Techniques regarding determining sufficiency of one or more machine learning models are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in memory. The computer executable components can comprise a measurement component that measures maximum deviation of a supervised learning model from a reference model over a certification set and an analysis component that determines sufficiency of the supervised learning model based at least in part on the maximum deviation.
    Type: Application
    Filed: September 13, 2022
    Publication date: March 21, 2024
    Inventors: Dennis Wei, Rahul Nair, Amit Dhurandhar, Kush Raj Varshney, Elizabeth Daly, Moninder Singh, Michael Hind
  • Patent number: 11914678
    Abstract: Techniques for classifier generalization in a supervised learning process using input encoding are provided. In one aspect, a method for classification generalization includes: encoding original input features from at least one input sample {right arrow over (x)}S with a uniquely decodable code using an encoder E(?) to produce encoded input features E({right arrow over (x)}S), wherein the at least one input sample {right arrow over (x)}S comprises uncoded input features; feeding the uncoded input features and the encoded input features E({right arrow over (x)}S) to a base model to build an encoded model; and learning a classification function {tilde over (C)}E(?) using the encoded model, wherein the classification function {tilde over (C)}E(?) learned using the encoded model is more general than that learned using the uncoded input features alone.
    Type: Grant
    Filed: September 23, 2020
    Date of Patent: February 27, 2024
    Assignee: International Business Machines Corporation
    Inventors: Hazar Yueksel, Kush Raj Varshney, Brian E. D. Kingsbury
  • Patent number: 11915131
    Abstract: In an approach to improve the efficiency of solving problem instances by utilizing a machine learning model to solve a sequential optimization problem. Embodiments of the present invention receive a sequential optimization problem for solving and utilize a random initialization to solve a first instance of the sequential optimization problem. Embodiments of the present invention learning, by a computing device a machine learning model, based on a previously stored solution to the first instance of the sequential optimization problem. Additionally, embodiments of the present invention generate, by the machine learning model, one or more subsequent approximate solutions to the sequential optimization problem; and output, by a user interface on the computing device, the one or more subsequent approximate solutions to the sequential optimization problem.
    Type: Grant
    Filed: November 23, 2020
    Date of Patent: February 27, 2024
    Assignee: International Business Machines Corporation
    Inventors: Kartik Ahuja, Amit Dhurandhar, Karthikeyan Shanmugam, Kush Raj Varshney
  • Publication number: 20230401438
    Abstract: A method, a neural network, and a computer program product are provided that provide training of neural networks with continued fractions architectures. The method includes receiving, as input to a neural network, input data and training the input data through a plurality of continued fractions layers of the neural network to generate output data. The input data is provided to each of the continued fractions layers as well as output data from a previous layer. The method further includes outputting, from the neural network, the output data. Each continued fractions layer of the continued fractions layers is configured to calculate one or more linear functions of its respective input and to generate an output that is used as the input for a subsequent continued fractions layer, each continued fractions layer configured to generate an output that is used as the input for a subsequent layer.
    Type: Application
    Filed: June 9, 2022
    Publication date: December 14, 2023
    Inventors: Isha Puri, Amit Dhurandhar, Tejaswini Pedapati, Karthikeyan Shanmugam, Dennis Wei, Kush Raj Varshney
  • Patent number: 11734585
    Abstract: A post-processing method, system, and computer program product for post-hoc improvement of instance-level and group-level prediction metrics, including training a bias detector that learns to detect a sample that has an individual bias greater than a predetermined individual bias threshold value with constraints on a group bias, applying the bias detector on a run-time sample to select a biased sample in the run-time sample having a bias greater than the predetermined individual bias threshold bias value, and suggesting a de-biased prediction for the biased sample.
    Type: Grant
    Filed: December 10, 2018
    Date of Patent: August 22, 2023
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Manish Bhide, Pranay Lohia, Karthikeyan Natesan Ramamurthy, Ruchir Puri, Diptikalyan Saha, Kush Raj Varshney
  • Publication number: 20230229943
    Abstract: A post-processing method, system, and computer program product for post-hoc improvement of instance-level and group-level prediction metrics, including training a bias detector on a payload data that learns to detect a sample in a customer model that has an individual bias greater than a predetermined individual bias threshold value with constraints on a group bias, suggesting, in the run-time, a de-biased prediction based on the selected biased sample by a de-biasing procedure, and an arbiter decides based on user feedback whether to use the de-biased prediction or an original prediction made prior to the de-biasing procedure from the customer model which is then used as an output.
    Type: Application
    Filed: March 23, 2023
    Publication date: July 20, 2023
    Inventors: Manish Bhide, Pranay Lohia, Karthikeyan Natesan Ramamurthy, Ruchir Puri, Diptikalyan Saha, Kush Raj Varshney
  • Patent number: 11586849
    Abstract: Techniques regarding mitigating bias in one or more machine learning models are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a model component that can evaluate a machine learning model at a plurality of threshold settings to generate a sample set and can define a relationship between a fairness metric and a utility metric of the machine learning model based on the sample set.
    Type: Grant
    Filed: January 17, 2020
    Date of Patent: February 21, 2023
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Yunfeng Zhang, Rachel Katherine Emma Bellamy, Kush Raj Varshney
  • Patent number: 11520830
    Abstract: Techniques for generating and searching semantic flow graphs are provided that include creating, by a system operatively coupled to a processor employing a semantic flow graph creation process, a semantic flow graph based on an ontology associated with a set of subjects and a raw flow graph determined from an analysis of a data set relating to the set of subjects and searching, by the system, the semantic flow graph to determine a subset of information of the semantic flow graph that is responsive to a query based on the query and information of the semantic flow graph.
    Type: Grant
    Filed: January 10, 2019
    Date of Patent: December 6, 2022
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Ioana Monica Baldini Soares, Evan Patterson, Kush Raj Varshney, Aleksandra Mojsilovic
  • Publication number: 20220343218
    Abstract: Embodiments relate to an input-encoding technique in conjunction with federation. Participating entities are arranged in a collaborative relationship. Each participating entity trains a machine learning model with an encoder on a training data set. The performance of each of the models is measured and at least one of the models is selectively identified based on the measured performance. An encoder of the selectively identified machine learning model is shared with each of the participating entities. The shared encoder is configured to be applied by the participating entities to train the first and second machine learning models, which are configured to be merged and shared in the federated learning environment.
    Type: Application
    Filed: April 26, 2021
    Publication date: October 27, 2022
    Applicant: International Business Machines Corporation
    Inventors: Hazar Yueksel, Brian E. D. Kingsbury, Kush Raj Varshney, Pradip Bose, Dinesh C. Verma, Shiqiang Wang, Augusto Vega, ASHISH VERMA, SUPRIYO CHAKRABORTY
  • Patent number: 11483154
    Abstract: A method for blockchain certification of artificial intelligence factsheets that includes receiving by a computing device, an artificial intelligence model. The computing device generates an artificial intelligence factsheet based upon logic of the artificial intelligence model. The computing device generates a blockchain link for a blockchain. The blockchain link certifies the artificial intelligence factsheet. The computing device transmits the blockchain link certifying the artificial intelligence factsheet to other computing devices.
    Type: Grant
    Filed: February 19, 2020
    Date of Patent: October 25, 2022
    Assignee: International Business Machines Corporation
    Inventors: Kalapriya Kannan, Pranay Kumar Lohia, Samuel Hoffman, Kush Raj Varshney, Sameep Mehta
  • Patent number: 11443236
    Abstract: A method of utilizing a computing device to correct source data used in machine learning includes receiving, by the computing device, first data. The computing device corrects the source data via an application of a covariate shift to the source data based upon the first data where the covariate shift re-weighs the source data.
    Type: Grant
    Filed: November 22, 2019
    Date of Patent: September 13, 2022
    Assignee: International Business Machines Corporation
    Inventors: Karthikeyan Natesan Ramamurthy, Amanda Coston, Dennis Wei, Kush Raj Varshney, Skyler Speakman, Zairah Mustahsan, Supriyo Chakraborty
  • Publication number: 20220180254
    Abstract: A method, computer system, and a computer program product for invariant risk minimization games is provided. The present invention may include defining a plurality of environment-specific classifiers corresponding to a plurality of environments. The present invention may also include constructing an ensemble classifier associated with the plurality of environment-specific classifiers. The present invention may further include initiating a game including a plurality of players corresponding to the plurality of environments. The present invention may also include calculating a nash equilibrium of the initiated game. The present invention may further include determining an ensemble predictor based on the calculated nash equilibrium. The present invention may include deploying the determined ensemble predictor associated with the calculated nash equilibrium to make predictions in a new environment.
    Type: Application
    Filed: December 8, 2020
    Publication date: June 9, 2022
    Inventors: Kartik Ahuja, Karthikeyan Shanmugam, Kush Raj Varshney, Amit Dhurandhar
  • Publication number: 20220164644
    Abstract: In an approach to improve the efficiency of solving problem instances by utilizing a machine learning model to solve a sequential optimization problem. Embodiments of the present invention receive a sequential optimization problem for solving and utilize a random initialization to solve a first instance of the sequential optimization problem. Embodiments of the present invention learning, by a computing device a machine learning model, based on a previously stored solution to the first instance of the sequential optimization problem. Additionally, embodiments of the present invention generate, by the machine learning model, one or more subsequent approximate solutions to the sequential optimization problem; and output, by a user interface on the computing device, the one or more subsequent approximate solutions to the sequential optimization problem.
    Type: Application
    Filed: November 23, 2020
    Publication date: May 26, 2022
    Inventors: Kartik Ahuja, Amit Dhurandhar, Karthikeyan Shanmugam, Kush Raj Varshney
  • Publication number: 20220092365
    Abstract: Techniques for classifier generalization in a supervised learning process using input encoding are provided. In one aspect, a method for classification generalization includes: encoding original input features from at least one input sample {right arrow over (x)}S with a uniquely decodable code using an encoder E(?) to produce encoded input features E({right arrow over (x)}S), wherein the at least one input sample {right arrow over (x)}S comprises uncoded input features; feeding the uncoded input features and the encoded input features E({right arrow over (x)}S) to a base model to build an encoded model; and learning a classification function {tilde over (C)}E(?) using the encoded model, wherein the classification function {tilde over (C)}E(?) learned using the encoded model is more general than that learned using the uncoded input features alone.
    Type: Application
    Filed: September 23, 2020
    Publication date: March 24, 2022
    Inventors: Hazar Yueksel, Kush Raj Varshney, Brian E.D. Kingsbury
  • Publication number: 20220037020
    Abstract: Analyzing complex systems by receiving labeled event data describing events occurring in association with a complex system, generating a first machine learning model according to the distribution of labeled event data, receiving state variable transition data describing state variable transitions occurring in association with a complex system, training a second machine learning model according to a combination of a distribution of state variable transitions and the first machine learning model, and using the second machine learning model to predict the effects of events upon state variables within the complex system according to new state variable transition and new labeled event data.
    Type: Application
    Filed: July 30, 2020
    Publication date: February 3, 2022
    Inventors: Debarun Bhattacharjya, Tian Gao, Nicholas Scott Mattei, Karthikeyan Shanmugam, Dharmashankar Subramanian, Kush Raj Varshney
  • Patent number: 11158098
    Abstract: Techniques facilitating using a distribution system for incentivizing and accelerating data driven scientific research are described herein. The distribution system can track the input of various parties involved in scientific research, and when a reward, monetary or otherwise, is realized for one or more outcomes of the scientific research, the distribution system can distribute the reward among the parties that provided the input. The relative levels and contributions of the parties can be tracked to ensure that an equitable portioning of the reward is realized. A directed graph can be formed based on the transactions, wherein the nodes correspond to entities, researchers, publications, and the edges correspond to relationships between the entities. The directed graph can be analyzed to determine the relative or absolute levels of contributions from each of the entities, and the rewards can be distributed based on the contribution levels.
    Type: Grant
    Filed: October 25, 2019
    Date of Patent: October 26, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Flavio du Pin Calmon, Kush Raj Varshney
  • Publication number: 20210258160
    Abstract: A method for blockchain certification of artificial intelligence factsheets that includes receiving by a computing device, an artificial intelligence model. The computing device generates an artificial intelligence factsheet based upon logic of the artificial intelligence model. The computing device generates a blockchain link for a blockchain. The blockchain link certifies the artificial intelligence factsheet. The computing device transmits the blockchain link certifying the artificial intelligence factsheet to other computing devices.
    Type: Application
    Filed: February 19, 2020
    Publication date: August 19, 2021
    Inventors: Kalapriya Kannan, Pranay Kumar Lohia, Samuel Hoffman, Kush Raj Varshney, Sameep Mehta
  • Publication number: 20210224605
    Abstract: Techniques regarding mitigating bias in one or more machine learning models are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a model component that can evaluate a machine learning model at a plurality of threshold settings to generate a sample set and can define a relationship between a fairness metric and a utility metric of the machine learning model based on the sample set.
    Type: Application
    Filed: January 17, 2020
    Publication date: July 22, 2021
    Inventors: Yunfeng Zhang, Rachel Katherine Emma Bellamy, Kush Raj Varshney