Federated Learning Acceleration Patent for Intelligent Personalized Services
Summary
USPTO published patent application US20260094005A1 by Korea Electronics Technology Institute for a client training acceleration method using federated learning for intelligent personalized services. The invention includes searching similar models in a repository, aggregating them into a global model, distributing to clients for training, and reflecting local data on the model. The application (No. 18941753) was filed on 2024-11-08 and published on 2026-04-02.
What changed
Korea Electronics Technology Institute filed patent application US20260094005A1 for a method of accelerating federated learning client training. The invention covers searching models with similarity above a predetermined threshold in a model repository based on user requests and embedded data, generating a weighted global model from searched models, distributing the global model to user and participating clients for training, and training the global model to reflect pre-stored local data. The patent is classified under CPC G06N 3/098.
This patent application does not create immediate compliance obligations for third parties. Technology companies developing federated learning systems, AI personalization engines, or distributed machine learning training infrastructure should review the published claims to assess potential patent landscape implications. The application represents a draft stage intellectual property claim that has not yet been examined or granted.
Archived snapshot
Apr 3, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
METHOD FOR ACCELERATING CLIENT TRAINING BASED ON FEDERATED LEARNING FOR INTELLIGENT PERSONALIZED SERVICES
Application US20260094005A1 Kind: A1 Apr 02, 2026
Assignee
Korea Electronics Technology Institute
Inventors
Young Hwan JEONG, Tae Min HWANG, Won Gi CHOI, Sang Shin LEE, Jin Young LEE
Abstract
According to an embodiment, a client training acceleration method includes: searching a model that has a similarity greater than or equal to a predetermined threshold value in a model repository, based on a user request and embedded data; generating a global model by aggregating the searched models with weights; distributing the global model to a user client and a participating client, and requesting training of the distributed global model; and training the global model to reflect pre-stored local on the distributed global model.
CPC Classifications
G06N 3/098
Filing Date
2024-11-08
Application No.
18941753
Named provisions
Related changes
Get daily alerts for USPTO Patent Applications - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - AI & Computing (G06N) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.