Motif-SocialRec: A Multi-channel Interactive Semantic Extraction Model for Social Recommendation

To capture complex interaction semantics beyond pairwise relationships for social recommendation, a novel recommendation model, namely Motif-SocialRec, is proposed under the perspective of motif. It efficiently describes interaction pattern from multi-channel with different motifs. In the model, we depict a series of local structures by motif, which can describe the high-level interactive semantics in the fused network from three views. By employing hypergraph convolution network, representations that preserve potential semantic patterns can be learned. Additionally, we enhance the learned representations by establishing self-supervised learning tasks on different scales to further explore the inherent characteristics of the network. Finally, a joint optimization model is constructed by integrating the primary and auxiliary tasks to produce recommendation predictions. Results of extensive experiments on four real-world datasets show that Motif-SocialRec significantly outperforms baselines in terms of different evaluation metrics.