Patents Assigned to Fairness-as-a-Service
  • DISPARITY MITIGATION IN MACHINE LEARNING-BASED PREDICTIONS FOR DISTINCT CLASSES OF DATA USING DERIVED INDISCERNIBILITY CONSTRAINTS DURING NEURAL NETWORK TRAINING
    Publication number: 20240135186
    Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine
    Type: Application
    Filed: December 27, 2023
    Publication date: April 25, 2024
    Applicant: Fairness-as-a-Service, Inc.
    Inventors: John Wickens-Lamb Merrill, Kareem Saleh, Mark Eberstein
  • Disparity mitigation in machine learning-based predictions for distinct classes of data using derived indiscernibility constraints during neural network training
    Patent number: 11934960
    Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine
    Type: Grant
    Filed: May 1, 2023
    Date of Patent: March 19, 2024
    Assignee: Fairness-as-a-Service
    Inventors: John Wickens-Lamb Merrill, Kareem Saleh, Mark Eberstein
  • DISPARITY MITIGATION IN MACHINE LEARNING-BASED PREDICTIONS FOR DISTINCT CLASSES OF DATA USING DERIVED INDISCERNIBILITY CONSTRAINTS DURING NEURAL NETWORK TRAINING
    Publication number: 20230267334
    Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine
    Type: Application
    Filed: May 1, 2023
    Publication date: August 24, 2023
    Applicant: Fairness-as-a-Service, Inc.
    Inventors: John Wickens-Lamb Merrill, Kareem Saleh, Mark Eberstein
  • Disparity mitigation in machine learning-based predictions for distinct classes of data using derived indiscernibility constraints during neural network training
    Patent number: 11676037
    Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine
    Type: Grant
    Filed: December 5, 2022
    Date of Patent: June 13, 2023
    Assignee: Fairness-as-a-Service, Inc.
    Inventors: John Wickens-Lamb Merrill, Kareem Saleh, Mark Eberstein