Recently, graph neural networks (GNNs) have been successfully applied to recommender systems as an effective collaborative filtering (CF) approach. The key idea of GNN-based recommender system is to recursively perform the message passing along the user-item interaction edge for refining the encoded embeddings, relying on sufficient and high-quality training data. Since user behavior data in practical recommendation scenarios is often noisy and exhibits skewed distribution, some recommendation approaches, e.g., SGL and SimGCL, leverage self-supervised learning to improve user representations against the above issues. Despite their effectiveness, however, they conduct self-supervised learning through creating contrastvie views, depending on the exploration of data augmentations with the problem of tedious trial-and-error selection of augmentation methods. In this paper, we propose a novel Adaptive Graph Contrastive Learning (AdaptiveGCL) framework which conducts graph contrastive learning with two adaptive contrastive view generators to better empower CF paradigm. Specifically, we use two trainable view generators, which are a graph generative model and a graph denoising model respectively, to create contrastive views. Two generators are able to create adaptive contrastive views, addressing the problem of model collapse and achieving adaptive contrastive learning. With two adaptive contrasive views, more additionally high-quality training signals will be introduced into the CF paradigm and help to alleviate the data sparsity and noise issues. Extensive experiments on three benchmark datasets demonstrate the superiority of our model over various state-of-the-art recommendation methods. Further visual analysis intuitively explains why our AdaptiveGCL outperforms existing contrastive learning approaches based on selected data augmentation methods.

翻译：近年来，图神经网络（GNN）作为有效的协同过滤（CF）方法已成功应用于推荐系统。基于GNN的推荐系统的核心思想是，依托充足且高质量的标注数据，通过沿用户-物品交互边递归执行消息传递来优化编码嵌入。由于实际推荐场景中的用户行为数据往往带有噪声且呈现偏态分布，部分推荐方法（如SGL和SimGCL）利用自监督学习改善用户表征以应对上述问题。尽管这些方法有效，但它们通过创建对比视图实现自监督学习，且依赖数据增强方法探索，存在繁琐的试错式增强方法选择问题。本文提出新颖的自适应图对比学习（AdaptiveGCL）框架，通过两个自适应对比视图生成器执行图对比学习，更有效地提升协同过滤范式。具体而言，我们采用两个可训练的视图生成器——图生成模型和图去噪模型——分别创建对比视图。这两个生成器能构建自适应对比视图，解决模型坍塌问题并实现自适应对比学习。通过两个自适应对比视图，更多高质量的训练信号将被引入协同过滤范式，有助于缓解数据稀疏性和噪声问题。在三个基准数据集上的大量实验表明，我们的模型优于各类先进的推荐方法。进一步的可视化分析直观解释了为何AdaptiveGCL能超越现有基于选定数据增强方法的对比学习方法。