Dual-Domain Collaborative Denoising for Social Recommendation

Social recommendation leverages social network to complement user-item interaction data for recommendation task, aiming to mitigate the data sparsity issue in recommender systems. The information propagation mechanism of graph neural networks (GNNs) aligns well with the process of social influence diffusion in social network, thereby can theoretically boost the performance of recommendation. However, existing social recommendation methods encounter the following challenge: both social network and interaction data contain substantial noise, and the propagation of such noise through GNNs not only fails to enhance recommendation performance but may also interfere with the model's normal training. However, despite the importance of denoising for social network and interaction data, only a limited number of studies have considered the denoising for social network and all of them overlook that for interaction data, hindering the denoising effect and recommendation performance. Based on this, we propose a novel model called dual-domain collaborative denoising for social recommendation (DCDSR). DCDSR comprises two primary modules: the structure-level collaborative denoising module and the embedding-space collaborative denoising module. In the structure-level collaborative denoising module, information from the interaction domain is first employed to guide social network denoising. Subsequently, the denoised social network is used to supervise the denoising of interaction data. The embedding-space collaborative denoising module devotes to resisting the noise cross-domain diffusion problem through contrastive learning with dual-domain embedding collaborative perturbation. Additionally, a novel contrastive learning strategy, named Anchor-InfoNCE, is introduced to better harness the denoising capability of contrastive learning. The model is jointly trained under a recommendation task and a contrastive learning task. Evaluating our model on three real-world datasets verifies that DCDSR has a considerable denoising effect, thus outperforms the state-of-the-art social recommendation methods.