METHOD, FEDERATED LEARNING SYSTEM, AND COMPUTER PROGRAM (VERTICAL FEDERATED LEARNING WITH COMPRESSED EMBEDDINGS)

Title:

METHOD, FEDERATED LEARNING SYSTEM, AND COMPUTER PROGRAM (VERTICAL FEDERATED LEARNING WITH COMPRESSED EMBEDDINGS)

Document Type and Number:

Japanese Patent JP2022181195

Kind Code:

A

Abstract:

To solve the following problem: standard VFL approaches may incur high communications overhead, due to the need for communicating embeddings between clients and a server.SOLUTION: A method includes: recreating an initial overall embedding based on initial compressed embeddings and initial labels; sending a current version of a server model, to each of client computing devices; obtaining, from the client computing devices updated compressed embeddings, the updated compressed embeddings being compressed by clustering, and updated cluster labels corresponding to the updated compressed embeddings; based on local training by the plurality of client computing devices with the overall embedding and the current server model, recreating an updated overall embedding based on the updated embeddings and the corresponding updated cluster labels; and locally training the server model based on the updated overall embedding.SELECTED DRAWING: Figure 2

Inventors:

WANG SHIQIANG
ANIRBAN DAS
TIMOTHY JOHN CASTIGLIA
STACY ELIZABETH PATTERSON

Application Number:

JP2022084275A

Publication Date:

December 07, 2022

Filing Date:

May 24, 2022

Export Citation:

Click for automatic bibliography generation Help

Assignee:

INT BUSINESS MASCHINES CORPORATION
RENSSELAER POLYTECH INST

International Classes:

G06N20/00; G06F9/50

Attorney, Agent or Firm:

Tadashi Taneichi
Kataoka Tadahiko
Patent Attorney Corporation RYUKA International Patent Office

Previous Patent: Fast startup control circuit

Next Patent: Apparatus and computer-implemented method for automatically generating negative samples for training...