Method for identifying authors based on heterogeneous embedding network model

Abstract

The invention presents a method for identifying authors based on heterogeneous embedding network model. The method for identifying authors mainly comprises the following parts, to be specific, node embedding, heterogeneous embedding network model, shared embedding, joint training, and inputting paper to recognize and identify authors. The process comprises the following steps, firstly, inputting anonymous papers, analyzing the papers to identify key information and constructing characteristic representations; utilizing a heterogeneous embedded network model of task-guide teaching and path strength, including a specific embedded sub model of a specified task and a general embedded sub model of the path strength to generate a joint target and then performing a joint training; and finally confirming a rank for possible authors and outputting the highest ranking, namely a real author. The method for identifying authors based on heterogeneous embedded network model breaks through the limit that the heterogeneity of network is ignored and only isomorphic networks can be handled in the conventional embedding due to the fact of utilizing the universal network embedding which is independent of a specific task. By utilizing the network embedding with the guide task and strengthened path, the method is more efficient when applied to recognizing the real author, as compared with the existing method.

Description

technical field [0001] The invention relates to the field of author identification, in particular to a method for identifying authors based on a heterogeneous network embedding model. Background technique [0002] Author identification is often used to automatically identify possible authors of anonymous papers and identify the source of anonymous comments. It has broad implications for general information retrieval and recommendation systems, such as when it is necessary to match queried documents with known targets. In this field, existing methods mostly rely on problem-specific feature engineering, which is time-consuming and non-transferable. However, if the method of network embedding is adopted, it faces two main limitations: one is to use a general embedding method, which is not related to specific tasks. The second is that it can only deal with homogeneous networks, while ignoring the heterogeneity of networks. Therefore, the technical means currently used to identi...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the time-consuming and non-transferable problems of existing methods, the purpose of the present invention is to provide a method for identifying authors based on a heterogeneous network embedding model, which uses task-guided and path-enhanced heterogeneous network embedding models, including task-specific embedding sub- A generic embedding submodel of model and path augmentation to determine the ranking of likely authors, making it more accurate and efficient in identifying real authors

Images