Social relations are often used as auxiliary information to address data sparsity and cold-start issues in social recommendations. In the real world, social relations among users are complex and diverse. Widely used graph neural networks (GNNs) can only model pairwise node relationships and are not conducive to exploring higher-order connectivity, while hypergraph provides a natural way to model high-order relations between nodes. However, recent studies show that social recommendations still face the following challenges: 1) a majority of social recommendations ignore the impact of multifaceted social relationships on user preferences; 2) the item homogeneity is often neglected, mainly referring to items with similar static attributes have similar attractiveness when exposed to users that indicating hidden links between items; and 3) directly combining the representations learned from different independent views cannot fully exploit the potential connections between different views. To address these challenges, in this article, we propose a novel method DH-HGCN++ for multiple social recommendations. Specifically, dual homogeneity (i.e., social homogeneity and item homogeneity) is introduced to mine the impact of diverse social relations on user preferences and enrich item representations. Hypergraph convolution networks with motifs are further exploited to model the high-order relations between nodes. Finally, cross-view contrastive learning is proposed as an auxiliary task to jointly optimize the DH-HGCN++. Real-world datasets are used to validate the effectiveness of the proposed model, where we use sentiment analysis to extract comment relations and employ the k-means clustering algorithm to construct the item-item correlation graph. Experiment results demonstrate that our proposed method consistently outperforms the state-of-the-art baselines on Top-N recommendations.

Social relations are often used as auxiliary information to improve recommendations. In the real-world, social relations among users are complex and diverse. However, most existing recommendation methods assume only single social relation (i.e., exploit pairwise relations to mine user preferences), ignoring the impact of multifaceted social relations on user preferences (i.e., high order complexity of user relations). Moreover, an observing fact is that similar items always have similar attractiveness when exposed to users, indicating a potential connection among the static attributes of items. Here, we advocate modeling the dual homogeneity from social relations and item connections by hypergraph convolution networks, named DH-HGCN, to obtain high-order correlations among users and items. Specifically, we use sentiment analysis to extract comment relation and use the k-means clustering to construct item-item correlations, and we then optimize those heterogeneous graphs in a unified framework. Extensive experiments on two real-world datasets demonstrate the effectiveness of our model.