[论文解读] Adaptive Graph Contrastive Learning for Recommendation

Yangqin Jiang, Chao Huang+1 more|arXiv (Cornell University)|May 18, 2023

Recommender Systems and Techniques被引用 8

一句话总结

AdaGCL 引入两个可训练的视图生成器（图生成器和图去噪）来为基于图的协同过滤创建自适应对比视图，在数据噪声或稀疏时显著提升推荐性能。

ABSTRACT

Graph neural networks (GNNs) have recently emerged as an effective collaborative filtering (CF) approaches for recommender systems. The key idea of GNN-based recommender systems is to recursively perform message passing along user-item interaction edges to refine encoded embeddings, relying on sufficient and high-quality training data. However, user behavior data in practical recommendation scenarios is often noisy and exhibits skewed distribution. To address these issues, some recommendation approaches, such as SGL, leverage self-supervised learning to improve user representations. These approaches conduct self-supervised learning through creating contrastive views, but they depend on the tedious trial-and-error selection of augmentation methods. In this paper, we propose a novel Adaptive Graph Contrastive Learning (AdaGCL) framework that conducts data augmentation with two adaptive contrastive view generators to better empower the CF paradigm. Specifically, we use two trainable view generators - a graph generative model and a graph denoising model - to create adaptive contrastive views. With two adaptive contrastive views, AdaGCL introduces additional high-quality training signals into the CF paradigm, helping to alleviate data sparsity and noise issues. Extensive experiments on three real-world datasets demonstrate the superiority of our model over various state-of-the-art recommendation methods. Our model implementation codes are available at the link https://github.com/HKUDS/AdaGCL.

研究动机与目标

• 解决基于图的协同过滤在推荐场景中的数据噪声与稀疏性问题。
• 引入带有两个可训练视图生成器的自监督自适应学习，以缓解过拟合与模型崩溃。
• 通过自适应对比视图提升基于 GNN 的推荐系统的鲁棒性与泛化能力。
• 在真实数据集上展示对现有基线的实证提升。

提出的方法

• 使用类似 LightGCN 的局部图消息传递编码器来学习用户/物品嵌入。
• 引入两种可训练的视图生成器：图生成模型（基于 VGAE）和图去噪模型，用于产生自适应对比视图。
• 对用户和物品表征应用对比学习，同一节点视图来自正样本对，来自不同节点的视图之间为负样本对。
• 用 BPR 指导的目标和正则项对生成视图和去噪视图进行训练，以鼓励信息丰富的视图生成。
• 在上层多任务设置中将主 CF 目标与 SSL 目标联合优化，同时在下层为视图生成器设定目标。
• 加入一个去噪层，学习边缘有效掩码以过滤噪声边并生成去噪视图。

实验结果

研究问题

• RQ1 AdaGCL 在真实数据集上的性能如何与现有最先进的推荐系统相比？
• RQ2 各组件（自适应视图、VGAE 生成器、去噪视图）对整体性能的贡献是什么？
• RQ3 AdaGCL 是否能比基线更有效地处理噪声与稀疏数据？
• RQ4 关键超参数如何影响 AdaGCL 的性能？

主要发现

• AdaGCL 在 Last.FM、Yelp、BeerAdvocate 数据集的 Recall@20/40 与 NDCG@20/40 上优于多种基线。
• 两个自适应视图生成器有助于避免模型崩溃并提供多样化、信息丰富的自监督信号。
• 生成视图与去噪视图互补：捕捉数据模式并降低噪声。
• 通过自适应视图的自监督增强相较非自适应或随机增强方法带来一致性提升。
• 消融研究表明自适应组件对性能提升具有显著贡献。