Nonindependent Session Recommendation Based on Ordinary Differential Equation

Zhenyu Yang,Mingyu Li,Guojing Liu,Mingge Zhang

doi:10.1155/2020/9290576

Zhenyu Yang, Mingyu Li + Show 2 more

Open Access

https://doi.org/10.1155/2020/9290576

Copy DOI

Abstract

The recommendation method based on user sessions is mainly to model sessions as sequences in the assumption that user behaviors are independent and identically distributed, and then to use deep semantic information mining through Deep Neural Networks. Nevertheless, user behaviors may be a nonindependent intention at irregular points in time. For example, users may buy painkillers, books, or clothes for different reasons at different times. However, this has not been taken seriously in previous studies. Therefore, we propose a session recommendation method based on Neural Differential Equations in an attempt to predict user behavior forward or backward from any point in time. We used Ordinary Differential Equations to train the Graph Neural Network and could predict forward or backward at any point in time to model the user's nonindependent sessions. We tested for four real datasets and found that our model achieved the expected results and was superior to the existing session-based recommendations.

Highlights

More and more researchers have focused on recommendation methods based on user sessions
We still use the idea of GNNs to model sessions, and Gated Graph Neural Networks (GGNNs) [19, 20] capture the complex transitions between items within the session
We propose a recommendation model based on Neural Ordinary Differential Equations (ODE): Sess-ODEnet. e model combines differential equations with gated graph neural networks to model complex sessions. e model derives the representation vector of each embedded item by representing the session as the structure of the conversation graph and through the Graph Neural Network

Summary

Introduction

More and more researchers have focused on recommendation methods based on user sessions. Compared to other methods of directly modeling the relationship between users and items, the session-based approach can bring more implicit feedback. These studies are based on the fact that user behaviors are independent of each other, but it is not the case in real life. Since the discretization of such data has been often undefined, leading to the direct use of neural networks to learn such data, there may be problems of data loss or inaccurate inconsistencies in certain time intervals At this time, we introduce Ordinary Differential Equations (ODE) [21,22,23] to make up for this shortcoming. We can get the potential trajectory at any point in time by solving the Ordinary Differential Equations [24], which allows us to make forward or backward predictions at any point in time

Objectives

Results

Conclusion