18523090. PRIVACY-PRESERVING GRAPHICAL MODEL TRAINING METHODS, APPARATUSES, AND DEVICES simplified abstract (Alipay (Hangzhou) Information Technology Co., Ltd.)
Contents
- 1 PRIVACY-PRESERVING GRAPHICAL MODEL TRAINING METHODS, APPARATUSES, AND DEVICES
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 PRIVACY-PRESERVING GRAPHICAL MODEL TRAINING METHODS, APPARATUSES, AND DEVICES - 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 GRAPHICAL MODEL TRAINING METHODS, APPARATUSES, AND DEVICES
Organization Name
Alipay (Hangzhou) Information Technology Co., Ltd.
Inventor(s)
PRIVACY-PRESERVING GRAPHICAL MODEL TRAINING METHODS, APPARATUSES, AND DEVICES - A simplified explanation of the abstract
This abstract first appeared for US patent application 18523090 titled 'PRIVACY-PRESERVING GRAPHICAL MODEL TRAINING METHODS, APPARATUSES, AND DEVICES
Simplified Explanation
The abstract describes a method for training graphical models using node information and latent vectors from multiple graphs, with gradient information being sent to a server for updating model parameters.
- Acquiring node information and latent vectors from multiple graphs
- Performing model training on a graphical model
- Sending gradient information to a server for updating model parameters
Potential Applications
This technology could be applied in various fields such as machine learning, data analysis, and pattern recognition.
Problems Solved
This technology helps in improving the accuracy and efficiency of graphical model training by utilizing information from multiple graphs and updating model parameters based on gradient information.
Benefits
The benefits of this technology include enhanced model training, better prediction accuracy, and improved performance of graphical models.
Potential Commercial Applications
One potential commercial application of this technology could be in developing advanced machine learning algorithms for industries such as healthcare, finance, and marketing.
Possible Prior Art
Prior art in the field of machine learning and graphical model training may include research papers, patents, and existing software tools that focus on similar techniques and methodologies.
Unanswered Questions
How does this method compare to traditional graphical model training techniques?
This article does not provide a direct comparison between this method and traditional graphical model training techniques. It would be interesting to know the specific advantages or limitations of this approach compared to more conventional methods.
What are the specific industries or research areas that could benefit the most from this technology?
While the potential applications are mentioned in the article, a more detailed exploration of the specific industries or research areas that could benefit the most from this technology would provide valuable insights for potential users or investors.
Original Abstract Submitted
Some embodiments of this specification disclose graphical model training methods, apparatuses, and devices. In an embodiment, a method performed by a terminal device includes: acquiring node information of a first graph to be constructed, node information of a second graph and node connection information of the second graph, acquiring a latent vector of a first node that has training label information in the first graph, acquiring latent vectors of the second node and the node in the second graph. performing, based on the first sample data and the second sample data, model training on a graphical model sent by a server, acquiring gradient information corresponding to the trained graphical model, and sending the gradient information to the server for the server to update model parameters in the graphical model based on gradient information provided by different terminal devices to obtain an updated graphical model.
