| CPC G06N 20/00 (2019.01) [G06F 16/27 (2019.01); G06F 16/289 (2019.01); G06N 5/02 (2013.01); G06Q 10/06375 (2013.01); H04L 63/20 (2013.01)] | 19 Claims |
|
1. A tangible, non-transitory, machine-readable medium storing instructions that when executed by one or more processors effectuate operations comprising:
receiving, with a computer system, a data token to be passed from a first node to a second node, wherein:
the first node and second nodes are members of a set of nodes participating in a federated machine-learning model executed by the computer system,
the federated machine-learning model comprises an application-layer network of sub-models of the federated machine-learning model,
different members of the set of nodes control different subsets of the sub-models in the application-layer network,
the data token corresponding to data upon which the federated machine-learning model operates, and
the data token is not among data upon which a sub-model of the second node was trained;
retrieving, with the computer system, machine learning model attributes from a collection of one or more of the sub-models of the federated machine-learning model;
determining, with the computer system, based on the machine learning model attributes, that the data token is learning relevant to members of the collection of one or more of the sub-models with means for statistics testing and, in response, adding the data token to a training set to be used by at least some members of the collection of one or more of the sub-models;
determining, with the computer system, a collection of data tokens to transmit from the second node to a third node of the set of nodes participating in a federated machine-learning model;
transmitting, with the computer system, the collection of data tokens from the second node to the third node across an interface between the second node and the third node;
obtaining, with the computer system, for a plurality of entities corresponding to the set of nodes, datasets, wherein:
the datasets comprise events involving the plurality of entities;
the datasets comprise or are otherwise associated with attributes of the plurality of entities; and
the events are distinct from the attributes;
forming, with the computer system, a plurality of objects, wherein each object of the plurality of objects comprises a different set of attributes and events;
forming, with the computer system, a library of classes with a plurality of object-orientation modelors;
forming, with the computer system, a plurality of object-manipulation functions, each function being configured to leverage a respective class among the library of classes;
receiving, with the computer system, a request from a first entity from the plurality of entities to determine a set of actions to achieve, or increase the likelihood of, a given targeted action;
assigning, with the computer system, the given targeted action to a first subset of classes from the library of classes;
determining, with the computer system, based on the assigning, the set of actions to achieve, or increase likelihood of, the given targeted action using a first subset of the plurality of object-manipulation functions leveraging the first subset of classes from the library of classes;
forming a third training dataset from the datasets;
training a third machine-learning model on the third training dataset by adjusting parameters of the third machine-learning model to optimize a third objective function that indicates interdependency of the plurality of object-manipulation functions in leveraging a specific class;
forming an interdependency graph using, at least in part, the third objective function, wherein the interdependency graph comprises a plurality of execution triggers, wherein each execution trigger from the plurality of execution triggers comprises a subset of the object-manipulation functions; and
storing the adjusted parameters of the trained third machine-learning model in memory.
|