Graph Neural Network(GNN) based social recommendation models improve the prediction accuracy of user preference by leveraging GNN in exploiting preference similarity contained in social relations. However, in terms of both effectiveness and efficiency of recommendation, a large portion of social relations can be redundant or even noisy, e.g., it is quite normal that friends share no preference in a certain domain. Existing models do not fully solve this problem of relation redundancy and noise, as they directly characterize social influence over the full social network. In this paper, we instead propose to improve graph based social recommendation by only retaining the informative social relations to ensure an efficient and effective influence diffusion, i.e., graph denoising. Our designed denoising method is preference-guided to model social relation confidence and benefits user preference learning in return by providing a denoised but more informative social graph for recommendation models. Moreover, to avoid interference of noisy social relations, it designs a self-correcting curriculum learning module and an adaptive denoising strategy, both favoring highly-confident samples. Experimental results on three public datasets demonstrate its consistent capability of improving two state-of-the-art social recommendation models by robustly removing 10-40% of original relations. We release the source code at https://github.com/tsinghua-fib-lab/Graph-Denoising-SocialRec.

翻译：基于图神经网络（GNN）的社交推荐模型通过利用GNN挖掘社交关系中蕴含的偏好相似性，提升了用户偏好预测的准确性。然而，从推荐效果和效率两方面来看，大量社交关系可能是冗余甚至带噪声的——例如，朋友之间在特定领域毫无共同偏好是常见现象。现有模型由于直接在整个社交网络上刻画社会影响，未能完全解决关系冗余与噪声问题。本文提出通过仅保留信息性社交关系来改进基于图的社交推荐，以确保高效且有效的影响力扩散，即图去噪。我们设计的去噪方法以偏好为导向来建模社交关系置信度，并通过为推荐模型提供去噪后更具信息量的社交图，反哺用户偏好学习。此外，为避免噪声社交关系的干扰，该方法设计了自校正课程学习模块与自适应去噪策略，两者均优先处理高置信度样本。在三个公开数据集上的实验结果表明，该方法能够稳定移除原始关系的10%-40%，并一致地提升两种最先进的社交推荐模型的性能。我们已开源代码：https://github.com/tsinghua-fib-lab/Graph-Denoising-SocialRec。