Recently, Graph Neural Networks (GNNs) achieve remarkable success in Recommendation. To reduce the influence of data sparsity, Graph Contrastive Learning (GCL) is adopted in GNN-based CF methods for enhancing performance. Most GCL methods consist of data augmentation and contrastive loss (e.g., InfoNCE). GCL methods construct the contrastive pairs by hand-crafted graph augmentations and maximize the agreement between different views of the same node compared to that of other nodes, which is known as the InfoMax principle. However, improper data augmentation will hinder the performance of GCL. InfoMin principle, that the good set of views shares minimal information and gives guidelines to design better data augmentation. In this paper, we first propose a new data augmentation (i.e., edge-operating including edge-adding and edge-dropping). Then, guided by InfoMin principle, we propose a novel theoretical guiding contrastive learning framework, named Learnable Data Augmentation for Graph Contrastive Learning (LDA-GCL). Our methods include data augmentation learning and graph contrastive learning, which follow the InfoMin and InfoMax principles, respectively. In implementation, our methods optimize the adversarial loss function to learn data augmentation and effective representations of users and items. Extensive experiments on four public benchmark datasets demonstrate the effectiveness of LDA-GCL.

翻译：近年来，图神经网络（GNN）在推荐系统中取得了显著成功。为缓解数据稀疏性问题，基于GNN的协同过滤方法采用图对比学习（GCL）提升性能。大多数GCL方法包含数据增强和对比损失（如InfoNCE），通过手工设计的图增强构造对比对，并最大化同一节点不同视图间的一致性（相对于其他节点），这被称为InfoMax原理。然而，不当的数据增强会阻碍GCL性能。InfoMin原理指出，优质视图集应共享最少信息，并为设计更优数据增强提供指导准则。本文首先提出一种新型数据增强方法（即边操作，包括边添加与边丢弃），进而基于InfoMin原理提出理论指导的对比学习框架——图对比学习可学习数据增强（LDA-GCL）。该方法包含数据增强学习与图对比学习，分别遵循InfoMin和InfoMax原理。在实现中，通过优化对抗损失函数来学习数据增强及用户与物品的有效表征。在四个公开基准数据集上的大量实验验证了LDA-GCL的有效性。