Method and device for obtaining network representation learning vector, equipment and storage medium

Abstract

The invention discloses a method and device for obtaining a network representation learning vector, equipment and a storage medium, belongs to the technical field of computers, and is used for enabling the representation learning vector to express more multilevel information on the basis that the calculation cost is as low as possible. The method comprises the following steps: constructing a social network association subgraph set according to social network data; obtaining a network representation learning initial vector of a non-central node included in the social network association subgraph set; for each sub-graph, obtaining a first attention weight from each non-central node to the forward edge of the central node, and obtaining an attention summary vector of the sub-graph according to the network representation learning initial vector of each non-central node and the first attention weight corresponding to each non-central node; and for each non-central node, obtaining a networkrepresentation learning adjustment vector of the non-central node according to the attention summary vector of the subgraph existing from the central node to the reverse edge of each non-central node.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method, device, equipment and storage medium for acquiring network representation learning vectors. Background technique [0002] The distributed representation of the network is a representation method of network data, which maps each node in the network to a K-dimensional vector space, and uses a K-dimensional vector to represent each node, and the node vector can also contain Certain semantic information, such as the distance between closely connected node vectors, is generally very similar in the vector space, so that a high-dimensional vector is represented as a low-dimensional dense real-valued vector. Representation learning is a way to obtain network representation learning vectors, which is the process of learning network representation learning vectors through machine learning methods, or using the similarity or correlation of network data itself to express ...

AI Technical Summary

Problems solved by technology

In network data, taking social networks as an example, there are many levels of information, including not only simple friends and follow relationships, but also complex relationships such as communities, discussion groups, interactions, and likes. Different levels include different information, while the representation learning vector obtained by the existing representation learning algorithm can only express a single level of information

Of course, there is also the integration of various information into the same network structure to learn heterogeneous networks, but this heterogeneous network is essentially equivalent to an expanded large network. For social networks, such a network scale increases. It is computationally unbearable, so under the same amount of calculation, the results obtained based on heterogeneous network learning algorithms are often not as good as general representation learning algorithms

Images