International Business Machines Corporation

Kush Raj Varshney

Lav Raj Varshney

Aleksandra Mojsilovic

Jun Li Wang

Ioana Monica Baldini Soares

Michael James Hind

Evan J Patterson

Roman Vaculin

Sekou Lionel Remy

Nelson Kibichii Bore

Ravi Kiran Raman

Eleftheria K Pissadaki

Amit Dhurandhar

Karthikeyan Natesan Ramamurthy

Flavio Du Pin Calmon

Florian Pinel

Sameep Mehta

Kalapriya Kannan

Pranay Kumar Lohia

Nizar Lethif

Karthikeyan Shanmugam

Mary Elizabeth Helander

Emily A Ray

Joana Sofia Branquinho Teresa Maria

Hemank Lamba

Nan Shao

Kartik Ahuja

Maja Vukovic

Manish Anand Bhide

Ruchir Puri

Ramya Raghavendra

Diptikalyan Saha

Supriyo Chakraborty

John Thomas Richards

Brian E D Kingsbury

Darrell Christopher Reimer

Rachel K E Bellamy

Manish Kesarwani

Matthew R Arnold

Kaoutar El Maghraoui

Jinfeng Yi

Yunfeng Zhang

Stephanie Houde

Skyler Speakman

Debarun Bhattacharjya

David John Piorkowski

Rachel Katherine Emma Bellamy

Dennis Wei

Jason Tsay

Samuel Chung Hoffman

Abhishek Kumar

Dongping Fang

Kien T Pham

John H Bauer

Amanda Coston

Zairah Mustahsan

Hazar Yueksel

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.

Learning robust predictors using game theory

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.

Representation of a data analysis using a flow graph

An example operation may include one or more of generating a plurality of successive data points of an iterative simulation based on predefined checkpoints, each data point identifying an evolving state of the iterative simulation with respect to a previous data point among the successive data points, transmitting a blockchain request for validating state data within a first data point among the plurality of successive data points to a first subset of endorsing nodes of a blockchain network, and transmitting a blockchain request for validating state data within a second data point among the plurality of successive data points to a second subset of endorsing nodes which are mutually exclusive from the first subset of endorsing nodes of the blockchain network for parallel endorsement of the first and second data points.

Distributed platform for computation and trusted validation

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.

Initializing optimization solvers

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)}with a uniquely decodable code using an encoder E(⋅) to produce encoded input features E({right arrow over (x)}), wherein the at least one input sample {right arrow over (x)}comprises uncoded input features; feeding the uncoded input features and the encoded input features E({right arrow over (x)}) to a base model to build an encoded model; and learning a classification function {tilde over (C)}(⋅) using the encoded model, wherein the classification function {tilde over (C)}(⋅) learned using the encoded model is more general than that learned using the uncoded input features alone.

Input encoding for classifier generalization

An example operation may include one or more of obtaining data of a simulation, identifying checkpoints within the simulation data, generating a plurality of sequential data structures based on the identified checkpoints, where each data structure identifies an evolving state of the simulation with respect to a previous data structure among the sequential data structures, and transmitting the generated sequential data structures to nodes of a blockchain network for inclusion in one or more data blocks within a hash-linked chain of data blocks.

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.

Post-hoc improvement of instance-level and group-level prediction metrics

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.

Mitigating statistical bias in artificial intelligence models

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.

Semantic queries based on semantic representation of programs and data source ontologies

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.

Artificial intelligence certification of factsheets using blockchain

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.

Enhancing fairness in transfer learning for machine learning models with missing protected attributes in source or target domains

A method for automatically generating documentation for an artificial intelligence model includes receiving, by a computing device, an artificial intelligence model. The computing device accesses a model facts policy that indicates data to be collected for artificial intelligence models. The computing device collects artificial intelligence model facts regarding the artificial intelligence model according to the model facts policy. The computing device accesses a factsheet template. The factsheet template provides a schema for an artificial intelligence model factsheet for the artificial intelligence model. The computing device populates the artificial intelligence model factsheet using the factsheet template with the artificial intelligence model facts related to the artificial intelligence model.

Generation and management of an artificial intelligence (AI) model documentation throughout its life cycle

The system, method, and computer program product are disclosed that track the evolution of a network over time through the analysis of media corpora associated with nodes of the network at each time slice. The media corpora may be analyzed to generate word clusters for each time slice that are then compared across time slices to determine how the network has evolved. The evolution may be tracked by determining the similarity of each word cluster of a particular time slice to each word cluster of another time slice. The similarity may be measured by a similarity score for each comparison that may be combined to determine an overall similarity of the network between the two time slices.

Tracking the evolution of topic rankings from contextual data

An example operation may include one or more of generating a data frame storing content of a simulation, compressing the simulation content within the data frame based on previous simulation content stored in another data frame to generate a compressed data frame, and transmitting the compressed data frame via a blockchain request to one or more endorsing peer nodes of a blockchain network for inclusion of the compressed data frame within a hash-linked chain of blocks of the blockchain network.

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.

Accelerating data-driven scientific discovery

Growing community of inventors

Ossining, NY, United States of America

Kush Raj Varshney