Citation recommendation algorithm based on heterogeneous network

Abstract

The invention discloses a citation recommendation algorithm based on a heterogeneous network. The citation recommendation algorithm specifically comprises the following steps: S1, constructing a binary heterogeneous citation network; s2, initializing author node vector representation vA and text content vector representation; s3, generating a structural information-based pacer vector representation; S4, generating a text information-based pacer vector representation; S5, performing joint interaction and mutual enhancement; S6, repeating the steps S4-5 until the model converges, and completingtraining; s7, obtaining final vectors of all the pasters and authentic in the training set, and storing the trained model; s8, calling the trained model parameters to obtain the vector representationof each follower in the test set; and S9, calculating cosine similarity of each follower in the test set and all the folders in the training set, sorting the folders from large to small according to the similarity, and taking the first K folders as a final recommendation result. According to the invention, the algorithm performance can be improved by combining the structure information, and the unknown document can be predicted.

Description

technical field [0001] The invention belongs to the technical field of machine learning, and in particular relates to a citation recommendation algorithm based on a heterogeneous network. Background technique [0002] Academic literature citation recommendation refers to automatically recommending appropriate citations and references for a given academic literature. With the help of citation recommendation, users can improve the efficiency of writing academic literature to a certain extent and reduce the omission of important relevant literature. lead. [0003] With the continuous development of deep learning, many deep learning methods have also been applied to citation recommendation and achieved good results. There are five common recommendation methods such as document similarity, topic model, translation model collaborative filtering and hybrid recommendation. Most methods are based on recommendation algorithms through citation networks, i.e., the network contains onl...

AI Technical Summary

Problems solved by technology

[0004] The structure-based deep learning algorithm requires that the document nodes in the test set exist in the training network, which converts the citation recommendation problem into link prediction, and has achieved good experimental results, but it cannot recommend unknown documents.

The content-based deep learning algorithm can solve this problem. It only depends on the text content in the learning process and can predict unknown documents, but the recommendation algorithm based solely on content is not effective.

Images