18154523. MULTI-GRAPH CONVOLUTION COLLABORATIVE FILTERING simplified abstract (HUAWEI TECHNOLOGIES CO., LTD.)
MULTI-GRAPH CONVOLUTION COLLABORATIVE FILTERING
Organization Name
Inventor(s)
Dengcheng Zhang of Shenzhen (CN)
Han Yuan of Hangzhou City (CN)
MULTI-GRAPH CONVOLUTION COLLABORATIVE FILTERING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18154523 titled 'MULTI-GRAPH CONVOLUTION COLLABORATIVE FILTERING
Simplified Explanation
The abstract describes a method and system for processing a bipartite graph, which consists of two types of nodes. The method involves generating embeddings (representations) for target nodes based on the features of neighboring nodes within a certain distance. The relationship between the target nodes is then determined based on these embeddings.
- The method processes a bipartite graph with two types of nodes.
- It generates embeddings for target nodes based on the features of neighboring nodes within a certain distance.
- The embeddings are used to determine the relationship between the target nodes.
Potential Applications
- Recommendation systems: The method can be used to analyze relationships between users and items in a recommendation system, improving the accuracy of recommendations.
- Social network analysis: It can help identify connections and relationships between different types of nodes in a social network, providing insights into user behavior and network structure.
- Fraud detection: By analyzing the relationships between different types of nodes in a network, the method can help identify suspicious patterns or connections indicative of fraudulent activity.
Problems Solved
- Complex graph analysis: The method provides a way to process and analyze bipartite graphs, which can be challenging due to the presence of two different types of nodes.
- Relationship determination: By generating embeddings and analyzing features of neighboring nodes, the method helps determine the relationship between target nodes, which can be useful in various applications.
Benefits
- Improved accuracy: The method's use of embeddings based on neighboring node features enhances the accuracy of relationship determination between target nodes.
- Scalability: The method can be applied to large-scale bipartite graphs, enabling efficient processing and analysis.
- Versatility: The method can be applied to various domains and applications, making it a versatile tool for analyzing bipartite graphs.
Original Abstract Submitted
Method and system for processing a bipartite graph that comprises a plurality of first nodes of a first node type, and a plurality of second nodes of a second type, comprising: generating a target first node embedding for a target first node based on features of second nodes and first nodes that are within a multi-hop first node neighbourhood of the target first node, the target first node being selected from the plurality of first nodes of the first node type; generating a target second node embedding for a target second node based on features of first nodes and second nodes that are within a multi-hop second node neighbourhood of the target second node, the target second node being selected from the plurality of second nodes of the second node type; and determining a relationship between the target first node and the target second node based on the target first node embedding and the target second node embedding.