Robert bosch gmbh (20240296667). BOOSTING GRAPH EXPLAINABILITY USING SELF-GUIDED DATA AUGMENTATION simplified abstract
BOOSTING GRAPH EXPLAINABILITY USING SELF-GUIDED DATA AUGMENTATION
Organization Name
Inventor(s)
Piyush Chawla of Columbus OH (US)
Thang Doan of Santa Clara CA (US)
BOOSTING GRAPH EXPLAINABILITY USING SELF-GUIDED DATA AUGMENTATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240296667 titled 'BOOSTING GRAPH EXPLAINABILITY USING SELF-GUIDED DATA AUGMENTATION
Simplified Explanation: The patent application describes a method for training a model to determine graph similarity by using pairs of aligned nodes and training losses.
Key Features and Innovation:
- Training a model for determining graph similarity
- Receiving two graphs as training inputs
- Applying the model to find pairs of aligned nodes and training losses
- Generating an augmented graph based on aligned nodes
- Refining the model based on training losses
Potential Applications: This technology can be applied in various fields such as:
- Bioinformatics
- Social network analysis
- Image recognition
- Fraud detection
Problems Solved:
- Efficiently determining graph similarity
- Improving accuracy in aligning nodes between graphs
- Enhancing the training process for graph models
Benefits:
- Increased accuracy in graph similarity determination
- Improved performance in various applications
- Enhanced model training for complex graphs
Commercial Applications: Title: Graph Similarity Model Training Technology for Enhanced Data Analysis This technology can be utilized in industries such as:
- Data analytics
- Machine learning
- Information retrieval systems
- Network security
Prior Art: Readers can explore prior art related to graph similarity models, node alignment techniques, and graph training methods in academic journals, patent databases, and research papers.
Frequently Updated Research: Stay updated on the latest advancements in graph similarity models, machine learning algorithms for graph analysis, and data mining techniques for complex networks.
Questions about Graph Similarity Model Training Technology: 1. How does this technology improve the accuracy of graph similarity determination? 2. What are the potential challenges in implementing this method in real-world applications?
1. A relevant generic question not answered by the article, with a detailed answer: How does this technology compare to existing methods for training models in graph analysis?
2. Another relevant generic question, with a detailed answer: What are the key factors to consider when applying this technology to different types of graphs in various industries?
Original Abstract Submitted
a method for training a model for determining graph similarity is disclosed. the method comprises receiving a first graph and a second graph as training inputs, the first graph and the second graph each including nodes connected by edges. the method further comprises applying a model to the first graph and the second graph to determine (i) pairs of aligned nodes between the first graph and the second graph and (ii) a first training loss. the method further comprises generating a first augmented graph by modifying the first graph depending on the pairs of aligned nodes. the method further comprises applying the model to the first graph and the first augmented graph to determine a second training loss. the method further comprises refining the model based on the first training loss and the second training loss.
