Discrete Trust-aware Matrix Factorization for Fast Recommendation

Abstract

Trust-aware recommender systems have received much attention recently for their abilities to capture the influence among connected users. However, they suffer from the efficiency issue due to large amount of data and time-consuming real-valued operations. Although existing discrete collaborative filtering may alleviate this issue to some extent, it is unable to accommodate social influence. In this paper we propose a discrete trust-aware matrix factorization (DTMF) model to take dual advantages of both social relations and discrete technique for fast recommendation. Specifically, we map the latent representation of users and items into a joint hamming space by recovering the rating and trust interactions between users and items. We adopt a sophisticated discrete coordinate descent (DCD) approach to optimize our proposed model. In addition, experiments on two real-world datasets demonstrate the superiority of our approach against other state-of-the-art approaches in terms of ranking accuracy and efficiency.

Personalized multi-faceted trust modeling to determine trust links in social media and its potential for misinformation management

“…Trust modeling in the context of recommender systems has been examined by several researchers, dating back to the seminal paper of O'Donovan and Smyth [31]. More recent work has examined such issues as addressing cold start recommendation using trust modeling [17] or examining how to speed up trust-aware recommendation through improvements from matrix factorization [15]. In this paper, trust-aware recommendation arises as a central element of the validation of our proposed framework.…”

“…It is feasible to model reputation or popularity without such personalization. However, given the sparsity of data in most networks, the cold start problem 15 , and computational limitations, it is not typically feasible to give each agent a completely distinct model. Our approach to personalization in Sect.…”

Efficient Retrieval of Matrix Factorization-Based Top-k Recommendations: A Survey of Recent Approaches

“…(Li et al, 2019) proposes Discrete Collaborative Hashing, a binary codes learning framework with neural collaborative filtering for efficient recommendation systems. (Guo et al, 2019) introduces discrete trust-aware matrix factorization (DTMF) model to take advantage of both social relations and discrete technique for fast recommendation. (Wang et al, 2019) exploits graph convolutional network (GCN) to model high-order feature from implicit feedback and distill the ranking information derived from GCN to binarized collaborative filtering to improve the efficiency of online recommendation.…”

Personalized multi-faceted trust modeling to determine trust links in social media and its potential for misinformation management

“…It is feasible to model reputation or popularity without such personalization. However, given the sparsity of data in most networks, the cold start problem 15 , and computational limitations, it is not typically feasible to give each agent a completely distinct model. Our approach to personalization in Section 3 was to determine clusters of similar users and learn trust link classifiers on the basis of these clusters.…”