Abstract: Embodiments are disclosed for a method. The method includes receiving feedback decision rules for multiple predictions by a trained machine learning model. generating a feedback rule set based on the feedback decision rules. The method further includes generating an updated training dataset based on an original training dataset and an updated feedback rule set. The updated feedback rule set resolves one or more conflicts of the feedback rule set, and the updated training dataset is configured to train the machine learning model to move a decision boundary. Generating the updated training dataset includes generating multiple updated training instances by applying one of the feedback decision rules to a training instance of the original training dataset.

Abstract: Techniques for generating explanations for machine learning (ML) are disclosed. These techniques include identifying an ML model, an output from the ML model, and a plurality of constraints, and generating a plurality of neighborhoods relating to the ML model based on the plurality of constraints. The techniques further include generating a predictor for each of the plurality of neighborhoods using the ML model and the plurality of constraints, constructing a combined predictor based on combining each of the respective predictors for the plurality of neighborhoods, and creating one or more explanations relating to the ML model and the output from the ML model using the combined predictor.

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to a process for providing an explanation result for an analytical model. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise an uncertainty component that determines an uncertainty score for a distribution of samples that neighbor a selected input to an analytical model, a sampling component that identifies a subset of the distribution of samples based on the uncertainty score, and an explanation component that generates an explanation of an output of the analytical model, corresponding to the selected input, based on use of a sample from the subset of the distribution of samples.

Abstract: Techniques for generating explanations for machine learning (ML) are disclosed. These techniques include identifying an ML model, an output from the ML model, and a plurality of constraints, and generating a plurality of neighborhoods relating to the ML model based on the plurality of constraints. The techniques further include generating a predictor for each of the plurality of neighborhoods using the ML model and the plurality of constraints, constructing a combined predictor based on combining each of the respective predictors for the plurality of neighborhoods, and creating one or more explanations relating to the ML model and the output from the ML model using the combined predictor.

Abstract: Embodiments of the invention provide a computer-implemented method that includes applying input representations of a three-dimensional (3D) domain to a generative neural network (GNN); and using the GNN to form a generative model of the 3D domain based at least in part on the input representations. The input representations include a global-shape input representation of the 3D domain.

Abstract: Obtain, from an existing machine learning classifier, original probabilistic scores classifying samples taken from two or more groups into two or more classes via supervised machine learning. Associate the original probabilistic scores with a plurality of original Lagrange multipliers. Adjust values of the plurality of original Lagrange multipliers via low-dimensional convex optimization to obtain updated Lagrange multipliers that satisfy fairness constraints as compared to the original Lagrange multipliers. Based on the updated Lagrange multipliers, closed-form transform the original probabilistic scores into transformed probabilistic scores that satisfy the fairness constraints while minimizing loss in utility. The fairness constraints are with respect to the two or more groups.

Abstract: A computer-implemented method, a computer program product, and a computer system for designing a fair machine learning model through user interaction. A computer system receives from a user a request for reviewing one or more biased subgroups in a dataset used in training a machine learning model and presents to the user the one or more biased subgroups and respective bias scores thereof. A computer system preprocesses the dataset to mitigate bias, in response to receiving from the user a request for mitigating the bias associated with the one or more biased subgroups. A computer system retrains the machine learning model, using a new dataset obtained from preprocessing the dataset. A computer system presents to the user respective new bias scores of the one or more biased subgroups in the new dataset. The user reviews the respective new bias scores to determine whether the fair machine learning model is built.

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.

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.

Abstract: Techniques for sanitization of machine learning (ML) models are provided. A first ML model is received, along with clean training data. A path is trained between the first ML model and a second ML model using the clean training data. A sanitized ML model is generated based on at least one point on the trained path. One or more ML functionalities are then facilitated using the sanitized ML model.

Abstract: A method for training a machine learning system using conditionally independent training data includes receiving an input dataset (p(x, y, z)). A generative adversarial network, that includes a generator and a first discriminator, uses the input dataset to generate a training data (ps (xf, yf, zf)) by generating the values (xf, yf, zf). The first discriminator determines a first loss (L1) based on (xf, yf, zf) and (x, y, z). A divergence calculator modifies the training data based on a dependence measure (?). The divergence calculator includes a second discriminator and a third discriminator. Modifying the training data includes receiving a reference value ({tilde over (y)}), and computing, by the second discriminator, a second loss (L2) based on (xf, yf, zf) and (xf, {tilde over (y)}, zf). The third discriminator computes a third loss (L3) based on (yf, zf) and ({tilde over (y)}, zf). Further, a fourth loss (L4) is computed based on L2 and L3.

Abstract: Define a similarity measure between first and second points in a data space by operation of a machine learning model. Generate interpretable representations of the first and second points. Generate an interpretable local description of the similarity measure by approximating the similarity measure as a distance between the interpretable representations of the first and second points. The distance between the interpretable representations incorporates a matrix. Learn values for the matrix through optimizing a loss function evaluated on perturbations of the first and second points. Explain a value of the similarity measure between the first and second points using elements of the matrix. Assess the explanation of the value of the similarity measure using a rubric. In response to the assessment of the explanation of the value of the similarity measure, modify the machine learning model. Deploy the modified machine learning model.

Abstract: Embodiments are disclosed for a method. The method includes receiving feedback decision rules for multiple predictions by a trained machine learning model. generating a feedback rule set based on the feedback decision rules. The method further includes generating an updated training dataset based on an original training dataset and an updated feedback rule set. The updated feedback rule set resolves one or more conflicts of the feedback rule set, and the updated training dataset is configured to train the machine learning model to move a decision boundary. Generating the updated training dataset includes generating multiple updated training instances by applying one of the feedback decision rules to a training instance of the original training dataset.

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.

Abstract: A method and system of stitching a plurality of image views of a scene, including grouping matched points of interest in a plurality of groups, and determining a similarity transformation with smallest rotation angle for each grouping of the matched points. The method further includes generating virtual matching points on non-overlapping area of the plurality of image views and generating virtual matching points on overlapping area for each of the plurality of image views.

Abstract: Obtain, from an existing machine learning classifier, original probabilistic scores classifying samples taken from two or more groups into two or more classes via supervised machine learning. Associate the original probabilistic scores with a plurality of original Lagrange multipliers. Adjust values of the plurality of original Lagrange multipliers via low-dimensional convex optimization to obtain updated Lagrange multipliers that satisfy fairness constraints as compared to the original Lagrange multipliers. Based on the updated Lagrange multipliers, closed-form transform the original probabilistic scores into transformed probabilistic scores that satisfy the fairness constraints while minimizing loss in utility. The fairness constraints are with respect to the two or more groups.

Abstract: Modularized data processing systems and methods for its use are provided. Processing a current job can reuse data generated for a previously processed job to the extent the two share parameter configurations. Similarly, outputs of processing modules generated during processing the previously processed job can be used as inputs to processing modules processing a current job, if the two jobs share some parameter configurations.

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.

Abstract: A method, system and apparatus of using a computing device to explain one or more predictions of a machine learning model including receiving by a computing device a pre-trained artificial intelligence model with one or more predictions, generating by the computing device a multilevel explanation tree, linking neighborhood of datapoints around each of a plurality of training datapoints to the one or more predictions, and utilizing by the computing device the multilevel explanation tree to explain one or more predictions of the machine learning model.

Abstract: Techniques for sanitization of machine learning (ML) models are provided. A first ML model is received, along with clean training data. A path is trained between the first ML model and a second ML model using the clean training data. A sanitized ML model is generated based on at least one point on the trained path. One or more ML functionalities are then facilitated using the sanitized ML model.