arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.08191cs.IRcs.LG
收藏

LightGCL:用于推荐的简单高效图对比学习方法

LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation

University of Hong Kong(香港大学)

Xuheng Cai, Chao Huang, Lianghao Xia, Xubin Ren

AI总结:

针对现有图对比学习推荐方法难保留语义结构、易受噪声干扰的问题,提出仅用奇异值分解做对比增强的LightGCL范式,在多个基准数据集上性能优于现有最优方法,且对数据稀疏性和流行度偏差鲁棒性更强。

摘要:

图神经网络(GNN)是基于图的推荐系统中一种强大的学习方法。近年来,结合对比学习的GNN凭借其数据增强策略在推荐任务中展现出优异性能,旨在处理高度稀疏的数据。尽管这类方法取得了成功,但现有大多数图对比学习方法要么在用户-物品交互图上执行随机增强(例如节点/边扰动),要么依赖基于启发式的增强技术(例如用户聚类)来生成对比视图。我们认为这些方法无法很好地保留内在语义结构,且容易受到噪声扰动的偏差影响。本文提出了一种简单高效的图对比学习范式LightGCL,可缓解这些损害基于对比学习的推荐器通用性与鲁棒性的问题。我们的模型仅利用奇异值分解进行对比增强,实现了结合全局协同关系建模的无约束结构细化。在多个基准数据集上开展的实验表明,该模型的性能较现有最优方法有显著提升。进一步分析证明了LightGCL在应对数据稀疏性和流行度偏差方面的优越性。该模型的源代码可在https://github.com/HKUDS/LightGCL获取。

英文摘要:

Graph neural network (GNN) is a powerful learning approach for graph-based recommender systems. Recently, GNNs integrated with contrastive learning have shown superior performance in recommendation with their data augmentation schemes, aiming at dealing with highly sparse data. Despite their success, most existing graph contrastive learning methods either perform stochastic augmentation (e.g., node/edge perturbation) on the user-item interaction graph, or rely on the heuristic-based augmentation techniques (e.g., user clustering) for generating contrastive views. We argue that these methods cannot well preserve the intrinsic semantic structures and are easily biased by the noise perturbation. In this paper, we propose a simple yet effective graph contrastive learning paradigm LightGCL that mitigates these issues impairing the generality and robustness of CL-based recommenders. Our model exclusively utilizes singular value decomposition for contrastive augmentation, which enables the unconstrained structural refinement with global collaborative relation modeling. Experiments conducted on several benchmark datasets demonstrate the significant improvement in performance of our model over the state-of-the-arts. Further analyses demonstrate the superiority of LightGCL's robustness against data sparsity and popularity bias. The source code of our model is available at https://github.com/HKUDS/LightGCL.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑