18520641. PRIVACY PRESERVING JOINT TRAINING OF MACHINE LEARNING MODELS simplified abstract (NEC Corporation)
Contents
- 1 PRIVACY PRESERVING JOINT TRAINING OF MACHINE LEARNING MODELS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 PRIVACY PRESERVING JOINT TRAINING OF MACHINE LEARNING MODELS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
PRIVACY PRESERVING JOINT TRAINING OF MACHINE LEARNING MODELS
Organization Name
Inventor(s)
Roberto Gonzalez Sanchez of Heidelberg (DE)
Vittorio Prodemo of Madrid (ES)
Marco Gramagiia of Madrid (ES)
PRIVACY PRESERVING JOINT TRAINING OF MACHINE LEARNING MODELS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18520641 titled 'PRIVACY PRESERVING JOINT TRAINING OF MACHINE LEARNING MODELS
Simplified Explanation
The abstract describes a method for training a shared machine learning model by generating a data transformation function, sharing it with other entities, creating private datasets, and training the model using these datasets.
- Explanation of the patent:
- A data transformation function is generated by a first entity.
- The function is shared with one or more second entities.
- The first entity creates a private dataset by applying the function to its own dataset.
- The first entity receives private datasets from the second entities, created using the shared function.
- A machine learning model is trained using these private datasets to produce a trained ML model.
Potential Applications
This technology can be applied in collaborative machine learning projects where multiple entities need to train a shared model while keeping their data private.
Problems Solved
This method allows entities to collaborate on training a machine learning model without sharing their raw data, addressing privacy concerns and enabling secure data sharing.
Benefits
- Enhanced privacy protection for sensitive data - Efficient collaboration on machine learning projects - Improved model performance through diverse training data sources
Potential Commercial Applications
"Secure Collaborative Machine Learning Model Training" can be utilized in industries such as healthcare, finance, and cybersecurity where data privacy is crucial for collaboration on machine learning projects.
Possible Prior Art
One possible prior art is the concept of federated learning, where models are trained across multiple decentralized devices without exchanging raw data.
Unanswered Questions
How does this method handle data synchronization between entities during model training?
The abstract does not provide details on how data synchronization is managed between entities to ensure consistency during model training.
What measures are in place to prevent data leakage or unauthorized access to private datasets?
The abstract does not mention specific security measures or protocols to prevent data leakage or unauthorized access to private datasets shared between entities.
Original Abstract Submitted
Systems and method for training a shared machine learning (ML) model. A method includes generating, by a first entity, a data transformation function; sharing, by the first entity, the data transformation function with one or more second entities; creating a first private dataset, by the first entity, by applying the data transformation function to a first dataset of the first entity; receiving one or more second private datasets, by the first entity, from the one or more second entities, each second private dataset having been created by applying the data transformation function to a second dataset of the second entity; and training a machine learning (ML) model using the first private dataset and the one or more second private datasets to produce a trained ML model.
