18290603. MODEL TRAINING USING FEDERATED LEARNING simplified abstract (LENOVO (SINGAPORE) PTE. LTD.)
Contents
MODEL TRAINING USING FEDERATED LEARNING
Organization Name
Inventor(s)
Dimitrios Karampatsis of Ruislip (GB)
Ishan Vaishnavi of München (DE)
MODEL TRAINING USING FEDERATED LEARNING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18290603 titled 'MODEL TRAINING USING FEDERATED LEARNING
Simplified Explanation: The patent application describes a method for model training using federated learning, where model parameters are aggregated from multiple sources.
Key Features and Innovation:
- Utilizes federated learning to aggregate model parameters from different sources.
- Enables the derivation of an aggregated trained model based on requirements provided by a network function.
- Discovers local model training logical functions to provide model parameters for aggregation.
- Transmits requests and responses to gather and aggregate model parameters effectively.
Potential Applications: This technology can be applied in various fields such as healthcare, finance, and telecommunications for collaborative model training.
Problems Solved: Addresses the challenge of aggregating model parameters from distributed sources for training a unified model.
Benefits:
- Improves model training efficiency by leveraging federated learning.
- Enhances privacy and security by keeping data decentralized during the training process.
Commercial Applications: Title: Enhanced Collaborative Model Training System This technology can be utilized by companies offering machine learning solutions, data analytics services, and AI platforms to improve model training processes and enhance data privacy.
Prior Art: Readers can explore prior research on federated learning, model aggregation techniques, and collaborative machine learning systems to understand the background of this technology.
Frequently Updated Research: Stay updated on the latest advancements in federated learning, distributed model training, and privacy-preserving machine learning techniques to enhance the effectiveness of this technology.
Questions about Model Training using Federated Learning: 1. How does federated learning ensure data privacy during the model training process? 2. What are the potential challenges of integrating federated learning into existing model training workflows?
Original Abstract Submitted
Apparatuses, methods, and systems are disclosed for model training using federated learning. One method includes receiving a first request from a network function which includes requirements to derive an aggregated trained model using federated learning from a local model training logical function. The method includes determining model parameters for aggregation using federated learning based on the requirements in the first request. The method includes discovering a local model training logical function that can provide model parameters for aggregation using federated learning based on the requirements. The method includes transmitting a second request to the local model training logical function to receive the model parameters. The method includes aggregating the model parameters using federated learning. The method includes transmitting a response including the aggregated model parameters.
