Learning to Rank with Trust and Distrust in Recommender Systems

Abstract

The data scarcity of user preferences and the coldstart problem often appear in real-world applications and limit the recommendation accuracy of collaborative filtering strategies. Leveraging the selections of social friends and foes can efficiently face both problems. In this study, we propose a strategy that performs social deep pairwise learning. Firstly, we design a ranking loss function incorporating multiple ranking criteria based on the choice in users, and the choice in their friends and foes to improve the accuracy in the top-k recommendation task. We capture the nonlinear correlations between user preferences and the social information of trust and distrust relationships via a deep learning strategy. In each backpropagation step, we follow a social negative sampling strategy to meet the multiple ranking criteria of our ranking loss function. We conduct comprehensive experiments on a benchmark dataset from Epinions, among the largest publicly available that has been reported in the relevant literature. The experimental results demonstrate that the proposed model beats other state-of-the art methods, attaining an 11.49% average improvement over the most competitive model. We show that our deep learning strategy plays an important role in capturing the nonlinear correlations between user preferences and the social information of trust and distrust relationships, and demonstrate the importance of our social negative sampling strategy on the proposed model.

A Collaborative Ranking Model with Multiple Location-based Similarities for Venue Suggestion

“…Lee et al [24] assumed that the user-item matrix is low rank within certain neighborhoods of the metric space and minimized a pair-wise loss function. Rafailidis and Crestani [32] proposed a model focusing on trust and distrust between users. They pushed the relevant items of users and their friends at the top of the list, while ranking low those of their foes.…”

Learning consumer and producer embeddings for user-generated content recommendation

“…Socially-Aware Recommendation: Leveraging social networks can help us understand user-user relationships and improve the performance of item recommendation [7,8,10,16]. The social network is usually based on friendship or 'trust' relationships.…”

Diversity-Ensured Semantic Movie Recommendation by Applying Linked Open Data

“…This listwise approach employs the derivative estimation of NDCG during training of LtR algorithm to assign the parameters of regression trees. Learning to rank model based recommender system [31] utilizes the trust and distrust relationships of the users and presents the most relevant items of the users and their friends at the top of the list. It presents the weighting strategy and captures the correlations between the user preferences based on the trust of the friends and distrust of the foes.…”