Information processing system, information processing device, information processing method, and program

The system addresses data errors in federated learning by detecting anomalies and implementing tailored recovery methods, ensuring continued learning accuracy and efficiency.

WO2026105762A1 Publication Date: 2026-05-21TOYOTA JIDOSHA KK
0 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2025/039565
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-11-15
Filing Date
2025-11-12
Publication Date
2026-05-21

AI Technical Summary

Technical Problem

Existing federated learning systems lack appropriate recovery processing methods when data errors occur, which can hinder correct model learning.

Method used

An information processing system with detection and control means to identify data anomalies and determine appropriate recovery methods, such as data correction, re-executing data alignment, or restarting learning, based on the type of error.

Benefits of technology

Enables effective recovery processing to maintain model accuracy by addressing data errors in federated learning, ensuring continued learning efficiency.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

An information processing system according to the present invention is made up of a plurality of participating nodes and performs federated learning on the basis of sequentially obtained local data. The information processing system includes a detecting means that detects a data abnormality in at least one of the plurality of participating nodes, and a control means that determines which of a plurality of countermeasures is to be implemented when a data abnormality occurs.
Need to check novelty before this filing date? Find Prior Art