Changchang C Liu

US Patent:

20210158099, May 27, 2021

Filed:

Nov 26, 2019

Appl. No.:

16/695268

Inventors:

- ARMONK NY, US
Shiqiang Wang - White Plains NY, US
Changchang Liu - White Plains NY, US
Bong Jun KO - Harrington Park NJ, US
Wei-Han Lee - White Plains NY, US

International Classification:

G06K 9/62
G06N 3/04
G06Q 10/10

Abstract:

A method, a computer program product, and a computer system determine when to perform a federated learning process. The method includes identifying currently available contributors among contributors of a federated learning task for which the federated learning process is to be performed. The method includes determining a usefulness metric of the currently available contributors for respective datasets from each of the currently available contributors used in performing the federated learning process. The method includes, as a result of the usefulness metric of the currently available contributors being at least a usefulness threshold, generating a recommendation to perform the federated learning process with the datasets of the currently available contributors. The method includes transmitting the recommendation to a processing component configured to perform the federated learning process.

US Patent:

20200125739, Apr 23, 2020

Filed:

Oct 19, 2018

Appl. No.:

16/164846

Inventors:

- Armonk NY, US
Supriyo Chakraborty - White Plains NY, US
Changchang Liu - White Plains NY, US

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 21/60
G06N 99/00
H04L 9/00
H04L 9/30

Abstract:

Distributed machine learning employs a central fusion server that coordinates the distributed learning process. Preferably, each of set of learning agents that are typically distributed from one another initially obtains initial parameters for a model from the fusion server. Each agent trains using a dataset local to the agent. The parameters that result from this local training (for a current iteration) are then passed back to the fusion server in a secure manner, and a partial homomorphic encryption scheme is then applied. In particular, the fusion server fuses the parameters from all the agents, and it then shares the results with the agents for a next iteration. In this approach, the model parameters are secured using the encryption scheme, thereby protecting the privacy of the training data, even from the fusion server itself.