A method of multi-attribute inference based on user node embedding

Abstract

The invention discloses a method of multi-attribute inference based on user node embedding. The method builds a user-commodity dual directed graph G with side weights and performs biased random walk thereon to obtain user-commodity sequences. The user-commodity sequences are placed in in a CBOW model for training to get the real value vector representation of all users in low-dimensional space. Amulti-attribute inference neural network model is constructed, and a multi-attribute inference model is obtained by training the low-dimensional vector representation of the user and corresponding multi-attribute representation as a training set. The real value vector representation of the user who needs to infer the user attribute in the low dimensional space is inputted into the trained multi-attribute inference model, and the multi-attribute values of the user are obtained. The invention can be applied to the fields closely related to user attributes such as defining different customer types in market analysis and mining user attribute information in depth to optimize personalized recommendation algorithm.

Description

technical field [0001] The invention belongs to the technical field of graph data mining, and more specifically, relates to a multi-attribute inference method based on User Node Embedding (UNE for short). Background technique [0002] Network embedding (also known as network representation learning) refers to embedding the nodes in the network into a low-dimensional vector space, so that the vector retains the topology information of the nodes in the network. Node embedding makes it possible to automatically learn low-dimensional features of nodes, and the learned feature representations can be used in many downstream machine learning tasks, so it has become one of the research hotspots in recent years. [0003] In the real world, a lot of data can be mapped into a network graph structure, such as social networks, citation networks, biological networks, etc. Using the definition of a graph, we can map any entity into a node in the graph, and the interaction between entities...

AI Technical Summary

Problems solved by technology

[0005] Most of the existing attribute inference methods use high-dimensional sparse feature dimensionality reduction to obtain user representation, ignoring the internal relationship between users, and the learned user representation has certain limitations.

Images