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: 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.

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.

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.

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.

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 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.

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.

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.

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.

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, 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.

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.

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.

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.

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.

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.

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.

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.