Group Recommendation via Self-Attention and Collaborative Metric Learning Model

Haiyan Wang,Yuliang Li,Felix Frimpong

doi:10.1109/access.2019.2953176

Abstract

Group recommendation has attracted wide attention owing to its significance in real applications. One of the big challenges for group recommendation systems is how to integrate individual preferences of each group member and attain overall preferences for the group. Most of the traditional group recommendation solutions regard group members as equal participants and assign a same weight to each member. As a result, performance of this type of recommendation methods is not as good as expected. To improve the performance of group recommendation, a novel group recommendation model via Self-Attention and Collaborative Metric Learning (SACML) is presented in this paper. With the employment of Self-Attention mechanism, the SACML model can learn the similarity interactions between group members and services and decide a different weight for different group member. Based on these weights, group preferences for services can be generated by the aggregation of group members’ preferences and the group’s own preference. Similar metric space between group and services is obtained via collaborative metric learning with the group preferences and positive and negative services’ features. Group recommendation is finally implemented based on the obtained metric space. Simulation has been conducted on CAMRa2011 and Meetup datasets, and experimental results show that the proposed SACML model has better performance in comparison with those baseline methods.

Highlights

Our motivation is to improve performance of group recommendation by calculating the similarity between group members’ preferences
The main contributions of this paper are as follows: 1. This paper proposes the SelfAttention and Collaborative Metric Learning (SACML) model which combines the self-attention mechanism with metric learning, and implements group recommendation
SACML MODEL This paper proposes a group recommendation method based on Self-Attention Collaborative Metric Learning (SACML) to recommend services to all members of a fixed group

Summary

Introduction

With the rapid development of information technology, the problem of information overload has become more and more serious. When faced with a large amount of information on the Internet, users find it hard to discover required and relevant information quickly and accurately according to their preferences. Recommendation systems have become one of the effective mitigation methods and an ideal recommendation method is supposed to be able to help users quickly find the services of interest. Many daily activities are carried out in the form of groups [1]. A group of friends planning to organize a dinner party, some scholars participating in an academic conference, and a group of customers who want to organize a group-buying activity.

Objectives

Results

Conclusion