Nowadays, it is more and more convenient for people to participate in group activities. Therefore, providing some recommendations to groups of individuals is indispensable. Group recommendation is the task of suggesting items or events for a group of users in social networks or online communities. In this work, we study group recommendation in a particular scenario, namely occasional group recommendation, which has few or no historical directly interacted items. Existing group recommendation methods mostly adopt attention-based preference aggregation strategies to capture group preferences. However, these models either ignore the complex high-order interactions between groups, users and items or greatly reduce the efficiency by introducing complex data structures. Moreover, occasional group recommendation suffers from the problem of data sparsity due to the lack of historical group-item interactions. In this work, we focus on addressing the aforementioned challenges and propose a novel group recommendation model called Self-Supervised Group Graph Collaborative Filtering (SGGCF). The goal of the model is capturing the high-order interactions between users, items and groups and alleviating the data sparsity issue in an efficient way. First, we explicitly model the complex relationships as a unified user-centered heterogeneous graph and devise a base group recommendation model. Second, we explore self-supervised learning on the graph with two kinds of contrastive learning module to capture the implicit relations between groups and items. At last, we treat the proposed contrastive learning loss as supplementary and apply a multi-task strategy to jointly train the BPR loss and the proposed contrastive learning loss. We conduct extensive experiments on three real-world datasets, and the experimental results demonstrate the superiority of our proposed model in comparison to the state-of-the-art baselines.

Nearest neighbor query processing is a fundamental problem that arises in many fields such as spatial databases and machine learning. ASPE, which uses invertible matrices to encrypt data, is a widely adopted Secure Nearest Neighbor (SNN) query scheme. Encrypting data by matrices is actually a linear combination of the multiple dimensions of the data, which is completely consistent with the relationship between the source signals and observed signals in the signal processing. By viewing dimensions of the data and the encrypted data as source signals and observed signals, respectively, we formally prove and experimentally demonstrate that ASPE is actually insecure against even ciphertext only attacks, using signal processing theory. Prior work proved that it is impossible to construct an SNN scheme even in much relaxed standard security models, we invalidate this hardness understanding by pointing out the incorrectness of the hardness proof.