Research On Session Recommendation Based On Graph Neural Network

Recommendation technology can solve the problem of information overload.It selects the information that the user is interested in from a large amount of information and recommends it to the user,so as to bring convenience to the user.Traditional research usually makes predictions based on past and long-term interact information for user,however,in many real applications,such long-term user information may not exist.Session recommendation,which can predict what the user will click based on the current session information.Previous researches on session recommendation have some problems.On the one hand,the model processes based on the current session.The model ignores the information in other sessions,and a large amount of potential information is not fully utilized.On the other hand,the user preference representation generated by the model is inaccurate,which leads to recommended results accuracy.For the above problems,it is very important to process based on click sequence and generate accurate recommendations.This paper proposes two methods,using the Pytorch framework,based on the graph neural network,the session recommendation is implemented.The specific work of this paper is as follows:(1)A session recommendation based on graph neural network and attention mechanism method was proposed.Firstly,the graph neural network was applied to capture the intrinsic connection of repeated clicks between items in order to obtain item embedding.Then,multi-head attention accurately represented global preferences,the global embedding was obtained,target attention activated the relevance of the target items with all items,target embedding was obtained.Finally,by fusing the local embedding,the ultimate session embedding was gained,and the next click was predicted.The comparison experiments were carried out on the public data sets.Experimental results show that,the proposed method is superior to the optimal benchmark method,P@20 reaches up to 71.74%and increases more than 0.3 percentage point,MRR@20 reaches up to 35.20%and increases more than 3 percentage point,verifying the effectiveness of the proposed method.(2)A session recommendation based on graph model and attention model method was proposed.Firstly,global graph model and session graph model were used to obtain neighborhood information and session information respectively,the item graph features were extracted through the graph neural network,global item representation and session item representation obtain two-level representations,which were combined with the graph embedding.Then,soft attention was used to fuse graph embedding and reverse position embedding,target attention activated the relevance of the target items,session embedding was generated through linear transformation.Finally,the recommended list of the N items for the next click was outputted through the prediction layer.The comparison experiments were carried out on the public data sets.Experimental results show that,the proposed method compared with the optimal method,P@20reaches 72.41% and MRR@20 reaches 35.34%,it is improved by 0.5 percentage point and 2 percentage point respectively,verifying the effectiveness of the proposed method.