International business machines corporation (20240242087). FEATURE SELECTION IN VERTICAL FEDERATED LEARNING simplified abstract
Contents
FEATURE SELECTION IN VERTICAL FEDERATED LEARNING
Organization Name
international business machines corporation
Inventor(s)
Timothy John Castiglia of Troy NY (US)
Nathalie Baracaldo Angel of San Jose CA (US)
Swanand Ravindra Kadhe of San Jose CA (US)
Shiqiang Wang of White Plains NY (US)
Stacy Elizabeth Patterson of Troy NY (US)
FEATURE SELECTION IN VERTICAL FEDERATED LEARNING - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240242087 titled 'FEATURE SELECTION IN VERTICAL FEDERATED LEARNING
The abstract of this patent application describes systems and techniques for feature selection in vertical federated learning. One embodiment includes a system with a memory storing computer executable components and a processor executing these components. The components include an aggregator machine learning model that aggregates embedding components from local machine learning models and removes certain components based on minimizing weights at an input layer.
- Vertical federated learning feature selection system
- Memory stores computer executable components
- Processor executes components
- Aggregator machine learning model aggregates embedding components
- Removes components based on minimizing weights at input layer
Potential Applications: - Enhancing privacy in federated learning systems - Improving efficiency of machine learning models - Customizing models for specific tasks or datasets
Problems Solved: - Addressing feature selection challenges in federated learning - Optimizing model performance by removing unnecessary components
Benefits: - Increased model accuracy and efficiency - Enhanced privacy protection for sensitive data - Tailored machine learning models for diverse applications
Commercial Applications: Title: "Enhancing Privacy and Efficiency in Federated Learning Systems" This technology could be utilized in industries such as healthcare, finance, and telecommunications to improve data privacy and model performance. Market implications include increased adoption of federated learning solutions in sensitive data environments.
Prior Art: Researchers can explore prior work on federated learning, feature selection techniques, and model aggregation methods to understand the evolution of this technology.
Frequently Updated Research: Stay informed on the latest advancements in federated learning, privacy-preserving machine learning, and model optimization techniques to enhance the application of this technology.
Questions about Vertical Federated Learning Feature Selection: 1. How does feature selection in vertical federated learning differ from traditional feature selection methods? 2. What are the key challenges in implementing feature selection in federated learning systems?
Original Abstract Submitted
systems and techniques that facilitate feature selection in vertical federated learning are provided. for example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. the system can also comprise a processor, operably coupled to the memory that can execute the computer executable components stored in memory. the computer executable components can comprise an aggregator machine learning model that aggregates a plurality of embedding components from one or more local machine learning models and removes one or more embedding components based on minimizing weights at an input layer of the aggregator machine learning model.