The explicitly observed social relations from online social platforms have been widely incorporated into recommender systems to mitigate the data sparsity issue. However, the direct usage of explicit social relations may lead to an inferior performance due to the unreliability (e.g., noises) of observed links. To this end, the discovery of reliable relations among users plays a central role in advancing social recommendation. In this paper, we propose a novel approach to adaptively identify implicit friends toward discovering more credible user relations. Particularly, implicit friends are those who share similar tastes but could be distant from each other on the network topology of social relations. Methodologically, to find the implicit friends for each user, we first model the whole system as a heterogeneous information network, and then capture the similarity of users through the meta-path based embedding representation learning. Finally, based on the intuition that social relations have varying degrees of impact on different users, our approach adaptively incorporates different numbers of similar users as implicit friends for each user to alleviate the adverse impact of unreliable social relations for a more effective recommendation. Experimental analysis on three real-world datasets demonstrates the superiority of our method and explain why implicit friends are helpful in improving social recommendation.

Recently, personalised search engines and recommendation systems have been widely adopted by users who require assistance in searching, classifying, and filtering information. This paper presents an overview of the field of personalisation systems and describes current state-of-the-art methods and techniques. It reviews approaches for (1) user profiling, including behaviour, preference, and intention modelling; (2) content modelling, comprising content representation, analysis, and classification; and (3) filtering methods for recommendation, classified into four main categories: rule-based, contentbased, collaborative, and hybrid filtering. The paper also discusses personalisation systems in different domains, and various techniques and their limitations. Finally, it identifies several issues and possible directions for further research that can improve recommendation capabilities and enhance personalised systems.

Recent reports from industry show that social recommender systems consistently fail in practice. According to the negative findings, the failure is attributed to: (1) a majority of users only have a very limited number of neighbors in social networks and can hardly benefit from relations; (2) social relations are noisy but they are often indiscriminately used; (3) social relations are assumed to be universally applicable to multiple scenarios while they are actually multi-faceted and show heterogeneous strengths in different scenarios. Most existing social recommendation models only consider the homophily in social networks and neglect these drawbacks.In this paper we propose a deep adversarial framework based on graph convolutional networks (GCN) to address these problems. Concretely, for the relation sparsity and noises problems, a GCN-based autoencoder is developed to augment the relation data by encoding high-order and complex connectivity patterns, and meanwhile is optimized subject to the constraint of reconstructing the original social profile to guarantee the validity of new identified neighborhood. After obtaining enough purified social relations for each user, a GCN-based attentive social recommendation module is designed to capture the heterogeneous strengths of social relations. These designs deal with the three problems faced by social recommender systems respectively. Finally, we adopt adversarial training to unify and intensify all components by playing a minimax game and ensure a coordinated effort to enhance social recommendation. Experimental results on multiple open datasets demonstrate the superiority of our framework and the ablation study confirms the importance and effectiveness of each component.

a b s t r a c tDue to the open nature of recommender systems, collaborative recommender systems are vulnerable to profile injection attacks, in which malicious users inject attack profiles into the rating matrix in order to bias the systems' ranking list. Recommender systems are highly vulnerable to shilling attacks, both by individuals and groups. Most of previous research focuses only on the differences between genuine profiles and attack profiles, ignoring the group characteristics in attack profiles of an attack. There also exist class unbalance problems in supervised detecting methods, the detecting performance is not as good when the amount of samples of attack profiles in training set is smaller. In this paper, we study the use of SVM based method and group characteristics in attack profiles. A two phase detecting method SVM-TIA is proposed based on these two methods. In the first phase, Borderline-SMOTE method is used to alleviate the class unbalance problem in classification; a rough detecting result is obtained in this phase; the second phase is a fine-tuning phase whereby the target items in the potential attack profiles set are analyzed. We conduct tests on the MovieLens 100 K Dataset and compare the performance of SVM-TIA with other shilling detecting methods to demonstrate the effectiveness of the proposed approach.