Session Recommendation Model Based on Context-Aware and Gated Graph Neural Networks.

Dan Li,Heng Liu,Qian Gao

doi:10.1155/2021/7266960

Abstract

The graph neural network (GNN) based approach has been successfully applied to session-based recommendation tasks. However, in the face of complex and changing real-world situations, the existing session recommendation algorithms do not fully consider the context information in user decision-making; furthermore, the importance of context information for the behavior model has been widely recognized. Based on this, this paper presents a session recommendation model based on context-aware and gated graph neural networks (CA-GGNNs). First, this paper presents the session sequence as data of graph structure. Second, the embedding vector representation of each item in the session graph is obtained by using the gated graph neural network (GGNN). In this paper, the GRU in GGNN is expanded to replace the input matrix and the state matrix in the conventional GRU with input context captured in the session (e.g., time, location, and holiday) and interval context (representing the proportion of the total session time of each item in the session). Finally, a soft attention mechanism is used to capture users' interests and preferences, and a recommendation list is given. The CA-GGNN model combines session sequence information with context information at each time. The results on the open Yoochoose and Diginetica datasets show that the model has significantly improved compared with the latest session recommendation methods.

Highlights

Nowadays, the amount of information on the Internet is exploding
We propose a session recommendation model based on context-aware and gated graph neural network, abbreviated as CA-GGNN, which is used to model session information and two kinds of context information in one framework
We can see that formulas (3)–(5) cannot meet the need for fusing contextual information. erefore, this paper extends the existing GGNN cycle elements. e input context and interval context presented in this paper are incorporated into the regular gate recurrent unit (GRU) cell. is makes the process of session recommendation dependent on session sequence information and on the session sequence and related context information. e specific extension methods are as follows

Summary

Introduction

The amount of information on the Internet is exploding. Recommendation system has become an essential tool to ease information overload and improve user experience. One of the main drawbacks is that they do not fully consider and analyze the relevance and contextual information between session items, such as input context related to user decisions, and time interval between user clicks on items. GNN-based session recommendation can use items as nodes to predict user behavior trends by effectively utilizing project-to-project relationships and content information. We propose a session recommendation model based on context-aware and gated graph neural network, abbreviated as CA-GGNN, which is used to model session information and two kinds of context information in one framework. E input matrix represents the scenario information of the external environment when the user makes the current decision, such as the time and place of the day. (1) is paper proposes a session recommendation model based on context and gated graph neural network.

Related Work

Experimental Results and Analysis

Method

Conclusion