arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.02544cs.IR
收藏

XSimGCL:面向推荐系统的极简图对比学习方法

XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation

Junliang Yu, Xin Xia, Tong Chen, Lizhen Cui, Nguyen Quoc Viet Hung, Hongzhi Yin

AI总结:

该研究揭示对比学习通过均匀表征缓解推荐系统流行度偏差的机制,提出摒弃图增强、采用噪声嵌入增强的极简XSimGCL方法,在准确率与训练效率上均优于现有图增强对比学习推荐方法。

摘要:

对比学习(CL)近期被证实对提升推荐系统性能至关重要。基于CL的推荐模型核心原理是保证从用户-物品二部图不同图增强得到的表征之间具有一致性。这种自监督方法能从原始数据中提取通用特征,从而缓解数据稀疏性问题。尽管该范式效果显著,但其性能提升的内在影响因素尚未被完全厘清。\n本文针对CL对推荐系统的影响提出了新的见解。研究发现,CL能让模型学习到分布更均匀的用户与物品表征,从而缓解普遍存在的流行度偏差,推动长尾物品的曝光。分析还表明,此前被认为不可或缺的图增强操作可靠性较低,在基于CL的推荐中作用有限。\n基于上述发现,本文提出一种面向推荐的极简图对比学习方法XSimGCL,该方法摒弃了无效的图增强操作,转而采用简单且有效的基于噪声的嵌入增强来生成CL所需的视图。在四个规模大、稀疏度高的基准数据集上开展的综合实验表明,尽管所提方法极为简单,却能平滑调节所学表征的均匀度,在推荐准确率和训练效率上均大幅优于基于图增强的同类方法。代码与所用数据集已发布于https://github.com/Coder-Yu/SELFRec。

英文摘要:

Contrastive learning (CL) has recently been demonstrated critical in improving recommendation performance. The underlying principle of CL-based recommendation models is to ensure the consistency between representations derived from different graph augmentations of the user-item bipartite graph. This self-supervised approach allows for the extraction of general features from raw data, thereby mitigating the issue of data sparsity. Despite the effectiveness of this paradigm, the factors contributing to its performance gains have yet to be fully understood. This paper provides novel insights into the impact of CL on recommendation. Our findings indicate that CL enables the model to learn more evenly distributed user and item representations, which alleviates the prevalent popularity bias and promoting long-tail items. Our analysis also suggests that the graph augmentations, previously considered essential, are relatively unreliable and of limited significance in CL-based recommendation. Based on these findings, we put forward an eXtremely Simple Graph Contrastive Learning method (XSimGCL) for recommendation, which discards the ineffective graph augmentations and instead employs a simple yet effective noise-based embedding augmentation to generate views for CL. A comprehensive experimental study on four large and highly sparse benchmark datasets demonstrates that, though the proposed method is extremely simple, it can smoothly adjust the uniformity of learned representations and outperforms its graph augmentation-based counterparts by a large margin in both recommendation accuracy and training efficiency. The code and used datasets are released at https://github.com/Coder-Yu/SELFRec.

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。

↑