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 2403.16656cs.LGcs.IR
收藏

用于推荐的图增强

Graph Augmentation for Recommendation

University of Hong Kong(香港大学);Aalborg University(奥尔堡大学)

Qianru Zhang, Lianghao Xia, Xuheng Cai, Siuming Yiu, Chao Huang, Christian S. Jensen

AI总结:

针对推荐系统中对比学习数据噪声及GNN过平滑问题,提出GraphAug框架,利用GIB正则化生成去噪自监督信号并自适应调整对比视图,显著提升推荐性能。

摘要:

图增强与对比学习因其能在标注数据有限时学习富有表达力的用户表示,在推荐系统领域受到广泛关注。然而,将现有GCL模型直接应用于真实推荐环境面临挑战,主要有两个问题。首先,对比学习未考虑数据噪声,会产生噪声自监督信号,导致性能下降。其次,许多现有GCL方法依赖图神经网络(GNN)架构,由于非自适应消息传递,易产生过平滑问题。为解决这些挑战,我们提出了一个原则性框架GraphAug。该框架引入了一个鲁棒的数据增强器,生成去噪的自监督信号,增强推荐系统。GraphAug框架结合了图信息瓶颈(GIB)正则化的增强范式,能自动提炼信息丰富的自监督信息,并自适应调整对比视图生成。通过在真实数据集上的严格实验,我们全面评估了GraphAug模型的性能,结果一致表明其优于现有基线方法。模型源代码公开于:https://github.com/HKUDS/GraphAug。

英文摘要:

Graph augmentation with contrastive learning has gained significant attention in the field of recommendation systems due to its ability to learn expressive user representations, even when labeled data is limited. However, directly applying existing GCL models to real-world recommendation environments poses challenges. There are two primary issues to address. Firstly, the lack of consideration for data noise in contrastive learning can result in noisy self-supervised signals, leading to degraded performance. Secondly, many existing GCL approaches rely on graph neural network (GNN) architectures, which can suffer from over-smoothing problems due to non-adaptive message passing. To address these challenges, we propose a principled framework called GraphAug. This framework introduces a robust data augmentor that generates denoised self-supervised signals, enhancing recommender systems. The GraphAug framework incorporates a graph information bottleneck (GIB)-regularized augmentation paradigm, which automatically distills informative self-supervision information and adaptively adjusts contrastive view generation. Through rigorous experimentation on real-world datasets, we thoroughly assessed the performance of our novel GraphAug model. The outcomes consistently unveil its superiority over existing baseline methods. The source code for our model is publicly available at: https://github.com/HKUDS/GraphAug.

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。

↑