International Business Machines Corporation

Parikshit Ram

Dakuo Wang

Radu Marinescu

Horst Cornelius Samulowitz

Gregory Bramble

Vaibhav Saxena

Alexander Gray

Daniel Karl I Weidele

Lior Horesh

Bei Chen

Akihiro Kishimoto

Bo Zhang

Yogish Sabharwal

Sijia Liu

Giacomo Nannicini

Deepak Vijaykeerthy

Martin Wistuba

Arunima Chaudhary

Abel Nicolas Valente

Aswin Kannan

Oktay Gunluk

Djallel Bouneffouf

Ashish Verma

Sanjeeb Dash

Saurabh Manish Raje

Ambrish Rwat

A plurality of objectives is received for a given dataset for an automated machine learning (autoML) process. A set of tradeoffs for the plurality of objectives are received that distribute weights to respective objectives. Pipelines are provided for the dataset that optimize each of the plurality of objectives according to the set of tradeoffs.

AutoML with multiple objectives and tradeoffs thereof

The exemplary embodiments disclose a method, a computer program product, and a computer system for determining that one or more model pipelines satisfy one or more constraints. The exemplary embodiments may include detecting a user uploading data, one or more constraints, and one or more model pipelines, collecting the data, the one or more constraints, and the one or more model pipelines, and determining that one or more of the model pipelines satisfies all of the one or more constraints based on applying one or more algorithms to the collected data, constraints, and model pipelines.

Machine learning with multiple constraints

A system, computer program product, and method are presented for performing multi-objective automated machine learning, and, more specifically, to identifying a plurality of machine learning pipelines as Pareto-optimal solutions to optimize a plurality of objectives. The method includes receiving input data directed toward one or more subjects of interest and determining a plurality of objectives to be optimized. The method also includes ingesting at least a portion of the input data through one or more machine learning (ML) models. The method further includes aggregating the plurality of objectives into one or more aggregated single objectives. The method also includes determining a plurality of Pareto-optimal solutions, thereby defining a plurality of ML pipelines that optimize the one or more aggregated single objectives. The method further includes selecting one ML pipeline from the plurality of ML pipelines.

Multi-objective automated machine learning

A system that provides a mathematical formulation for new problem of model validation and model selection in presence of test data feedback. The system comprises a memory that stores computer-executable components. A processor, operably coupled to the memory, executes the computer-executable components stored in the memory. A selection component selects a metric of performance evaluation accuracy; and a configuration component configures performance evaluation schemes for machine learning algorithms. A characterization component employs a supervised learning-based approach to characterize relationship between the configuration of the performance evaluation scheme and fidelity of performance estimates; and an optimization component that optimizes accuracy of the machine learning algorithms as a function of size of training data set relative to size of validation data set through selection of values associated with the configuration parameters.

Methods for automatically configuring performance evaluation schemes for machine learning algorithms

Systems, computer-implemented methods, and computer program products to facilitate automated generation of a machine learning pipeline based on a pipeline grammar are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a pipeline structure generator component that generates a machine learning pipeline structure based on a pipeline grammar. The computer executable components can further comprise a pipeline optimizer component that selects one or more machine learning modules that achieve a defined objective to instantiate a machine learning pipeline based on the machine learning pipeline structure.

Automated generation of a machine learning pipeline

A processor may include a set of primitive operators, receive a set of data-driven operators, at least one of the set of data-driven operators including a machine learning model, and receive an input-output data pair set. Based on a grammar specifying rules for linking the set of primitive operators and the set of data-driven operators, the processor may search among the set of primitive operators and the set of data-driven operators to find a symbolic model that fits the input-output data set.

Free-form integration of machine learning model primitives

Systems, computer-implemented methods, and computer program products to facilitate conditional parallel coordinates in automated artificial intelligence with constraints are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a visualization component that renders a pipeline constraint as a constraint axis having constraint scores of machine learning pipelines in a conditional parallel coordinates visualization. The computer executable components can further comprise a model generation component that generates a machine learning model based on the constraint scores of the machine learning pipelines.

Conditional parallel coordinates in automated artificial intelligence with constraints

A conditional parallel coordinate visualization system is provided. The system presents a parallel coordinate visualization that includes a set of parallel main axes that respectively correspond to a set of main dimensions. The system receives a first multivariate data including values at the set of main dimensions. The first multivariate data has a first additional data that includes values in a first set of sub-dimensions. The first set of sub-dimensions is associated with a first predicate value at a first predicate dimension in the set of main dimensions. The system presents the first multivariate data as a polyline that intersects the set of parallel main axes. Upon a selection of an option item, the system unfolds the parallel coordinate visualization to reveal a first set of parallel sub-axes that correspond to the first set of sub-dimensions. The system presents the first additional data at the first set of parallel sub-axes.

Conditional parallel coordinates

Growing community of inventors

Cambridge, MA, United States of America

Parikshit Ram