US 2022/0101175 A1 · INCREMENTAL AND DECENTRALIZED MODEL PRUNING IN FEDERATED MACHINE LEARNING

Abstract

A computer-implemented method, a computer program product, and a computer system for incremental and decentralized pruning of a machine learning model in federated learning. A federated learning system determines a serial sequence of participating in model pruning by agents in the federated learning system. A server in the federated learning system sends, to a first agent in the serial sequence, an initial model to trigger a federated pruning process for the machine learning model. The each of agents in the serial sequence prunes the machine learning model. The each of agents in the serial sequence generates an intermediately pruned model for an immediately next agent to prune. A final agent in the serial sequence prunes the machine learning model and generates a finally pruned model. The final agent sends the finally pruned model to the server.

Claims20

Dependent claims

A computer-implemented method for incremental and decentralized pruning of a machine learning model in federated learning, the method comprising:

determining, by a federated learning system, a serial sequence of participating in model pruning by agents in the federated learning system;
sending, by a server in the federated learning system, to a first agent in the serial sequence, an initial model to trigger a federated pruning process for the machine learning model;
pruning, by the first agent, the initial model;
pruning, by each of ones after the first agent in the serial sequence, a model that has been pruned by an immediately previous agent;
generating, by each of ones prior to a final agent in the serial sequence, an intermediately pruned model for an immediately next agent to prune;
generating, by the final agent, a finally pruned model;
and
sending, by the final agent, to the server, the finally pruned model.

5 more elements

A computer program product for incremental and decentralized pruning of a machine learning model in federated learning, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors, the program instructions executable to:

determine, by a federated learning system, a serial sequence of participating in model pruning by agents in the federated learning system;
send, by a server in the federated learning system, to a first agent in the serial sequence, an initial model to trigger a federated pruning process for the machine learning model;
prune, by the first agent, the initial model;
prune, by each of ones after the first agent in the serial sequence, a model that has been pruned by an immediately previous agent;
generate, by each of ones prior to a final agent in the serial sequence, an intermediately pruned model for an immediately next agent to prune;
generate, by the final agent, a finally pruned model;
and
send, by the final agent, to the server, the finally pruned model.

5 more elements

A computer system for incremental and decentralized pruning of a machine learning model in federated learning, the computer system comprising one or more processors, one or more computer readable tangible storage devices, and program instructions stored on at least one of the one or more computer readable tangible storage devices for execution by at least one of the one or more processors, the program instructions executable to:

determine, by a federated learning system, a serial sequence of participating in model pruning by agents in the federated learning system;
send, by a server in the federated learning system, to a first agent in the serial sequence, an initial model to trigger a federated pruning process for the machine learning model;
prune, by the first agent, the initial model;
prune, by each of ones after the first agent in the serial sequence, a model that has been pruned by an immediately previous agent;
generate, by each of ones prior to a final agent in the serial sequence, an intermediately pruned model for an immediately next agent to prune;
generate, by the final agent, a finally pruned model;
and
send, by the final agent, to the server, the finally pruned model.

5 more elements

Dependencies are inferred from the claim text.

Incremental and decentralized model pruning in federated machine learning

Life of this patent

Incremental and decentralized model pruning in federated machine learning

Life of this patent

Abstract

Claims20