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.

Abstract: One or more group-specific aggregate losses, one or more group-agnostic aggregate losses, and a joint loss are computed. A regularizer loss is computed based on the one or more group-specific aggregate losses and the one or more group-agnostic aggregate losses. One or more group-specific models are trained based on the one or more group-specific aggregate losses. A feature extractor is updated based on the regularizer loss and a joint classifier is updated based on the joint loss.

Abstract: In an embodiment, a method for generating contrastive information for a classifier prediction comprises receiving image data representative of an input image, using a deep learning classifier model to predict a first classification for the input image, evaluating the input image using a plurality of classifier functions corresponding to respective high-level features to identify one or more of the high-level features absent from the input image, and identifying, from among the high-level features absent from the input image, a pertinent-negative feature that, if added to the input image, will result in the deep learning classifier model predicting a second classification for the modified input image, the second classification being different from the first classification. In an embodiment, the method includes creating a pertinent-positive image that is a modified version of the input image that has the first classification and fewer than all superpixels of the input image.

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: Examples described herein provide a computer-implemented method that includes training, by one or more processing devices, a first neural network for classification based on training data in accordance with a first learning objective, the first neural network producing an intermediate feature function and a final feature function as outputs. The computer-implemented method further includes training, by the one or more processing devices, a second neural network for classification based on the intermediate feature function and the final feature function and further based at least in part on target task samples in accordance with a second learning objective. Training the second neural network includes computing maximal correlation functions of each of the intermediate feature function, the final feature function, and the target task samples.

Abstract: In an embodiment, a method for generating contrastive information for a classifier prediction comprises receiving image data representative of an input image, using a deep learning classifier model to predict a first classification for the input image, evaluating the input image using a plurality of classifier functions corresponding to respective high-level features to identify one or more of the high-level features absent from the input image, and identifying, from among the high-level features absent from the input image, a pertinent-negative feature that, if added to the input image, will result in the deep learning classifier model predicting a second classification for the modified input image, the second classification being different from the first classification. In an embodiment, the method includes creating a pertinent-positive image that is a modified version of the input image that has the first classification and fewer than all superpixels of the input image.

Abstract: With at least one hardware processor, obtain data specifying: two trained neural network models; and alignment data. With the at least one hardware processor, carry out neuron alignment on the two trained neural network models using the alignment data to obtain two aligned models. With the at least one hardware processor, train a minimal loss curve between the two aligned models. With the at least one hardware processor, select a new model along the minimal loss curve that maximizes accuracy on adversarially perturbed data.

Abstract: In an embodiment, a method for generating contrastive information for a classifier prediction comprises receiving image data representative of an input image, using a deep learning classifier model to predict a first classification for the input image, evaluating the input image using a plurality of classifier functions corresponding to respective high-level features to identify one or more of the high-level features absent from the input image, and identifying, from among the high-level features absent from the input image, a pertinent-negative feature that, if added to the input image, will result in the deep learning classifier model predicting a second classification for the modified input image, the second classification being different from the first classification. In an embodiment, the method includes creating a pertinent-positive image that is a modified version of the input image that has the first classification and fewer than all superpixels of the input image.

Abstract: Examples described herein provide a computer-implemented method that includes training, by one or more processing devices, a first neural network for classification based on training data in accordance with a first learning objection, the first neural network producing an intermediate feature function and a final feature function as outputs. The computer-implemented method further includes training, by the one or more processing devices, a second neural network for classification based on the intermediate feature function and the final feature function and further based at least in part on target task samples in accordance with a second learning objective. Training the second neural network includes computing maximal correlation functions of each of the intermediate feature function, the final feature function, and the target task samples.

Abstract: In an embodiment, a method for generating contrastive information for a classifier prediction comprises receiving image data representative of an input image, using a deep learning classifier model to predict a first classification for the input image, evaluating the input image using a plurality of classifier functions corresponding to respective high-level features to identify one or more of the high-level features absent from the input image, and identifying, from among the high-level features absent from the input image, a pertinent-negative feature that, if added to the input image, will result in the deep learning classifier model predicting a second classification for the modified input image, the second classification being different from the first classification. In an embodiment, the method includes creating a pertinent-positive image that is a modified version of the input image that has the first classification and fewer than all superpixels of the input image.

Abstract: Methods and systems for recovering corrupted/degraded images using approximations obtained from an ensemble of multiple sparse models are disclosed. Sparse models may represent images parsimoniously using elementary patterns from a “dictionary” matrix. Various embodiments of the present disclosure involve simple and computationally efficient dictionary design approach along with low-complexity reconstruction procedure that may use a parallel-friendly table-lookup process. Multiple dictionaries in an ensemble model may be inferred sequentially using greedy forward-selection approach and can incorporate bagging/boosting strategies, taking into account application-specific degradation. Recovery performance obtained using the proposed approaches with image super resolution and compressive recovery can be comparable to or better than existing sparse modeling based approaches, at reduced computational complexity.

Abstract: Methods and systems for recovering corrupted/degraded images using approximations obtained from an ensemble of multiple sparse models are disclosed. Sparse models may represent images parsimoniously using elementary patterns from a “dictionary” matrix. Various embodiments of the present disclosure involve simple and computationally efficient dictionary design approach along with low-complexity reconstruction procedure that may use a parallel-friendly table-lookup process. Multiple dictionaries in an ensemble model may be inferred sequentially using greedy forward-selection approach and can incorporate bagging/boosting strategies, taking into account application-specific degradation. Recovery performance obtained using the proposed approaches with image super resolution and compressive recovery can be comparable to or better than existing sparse modeling based approaches, at reduced computational complexity.