Heterogeneous graph embedding learning method based on attention mechanism

Abstract

The invention discloses a heterogeneous graph embedding learning method based on an attention mechanism. The heterogeneous graph embedding learning method comprises the following steps: step 1, converting all nodes in a heterogeneous graph into a unified feature space through a type conversion matrix; 2, designing attention weights of a type-level attention learning given node for different types of neighbors; step 3, designing a neighbor node attention weight of node-level attention learning based on a meta-path, and performing weighted aggregation according to the attention weight to obtain node embedding based on a specific meta-path; 4, designing attention weights of different meta-paths of semantic-level attention learning, and performing weighted aggregation on node embedding based on different meta-paths according to the attention weights to obtain final node embedding; step 5, performing prediction training on the node labels; and step 6, designing a loss function, and performing model optimization training by using a back propagation algorithm. The work of the invention provides a new research thought for how to apply the attention mechanism to the heterogeneous graph.

Description

technical field [0001] The invention relates to an attention mechanism-based heterogeneous graph embedding learning method, which belongs to the fields of graph neural network and artificial intelligence. Background technique [0002] In recent years, a special type of graph called Heterogeneous Information Graph (HIN) has become a hot research topic in web mining. Heterogeneous graphs of matrices and nodes represent complex relationships, such as recommender systems, paper citation networks, etc. The most important feature of HIN is the meta-path, which reflects the semantic relationship in node-edge tuples. Taking the paper citation network as an example, the relationship between two papers can be regarded as Paper-Author-Paper illustration (co-author relationship) and Paper-Subject-Paper (same subject relationship). From the tuples listed above, we can see that in a heterogeneous graph, different connection patterns contain different relations, and traditional deep netw...

AI Technical Summary

Problems solved by technology

Compared with isomorphic graph embedding learning, heterogeneous graphs are more complex

Images