Graph Collaborative Signals Denoising and Augmentation for Recommendation
Graph Collaborative Signals Denoising and Augmentation for Recommendation
复制标题
DOI：
10.1145/3539618.3591994
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Ziwei Fan;Ke Xu;Zhang Dong;Hao Peng;Jiawei Zhang;Philip S. Yu
中科院分区：
文献类型：
--
作者：
Ziwei Fan;Ke Xu;Zhang Dong;Hao Peng;Jiawei Zhang;Philip S. Yu
图协同过滤(GCF)是推荐系统中捕获高阶协同信号的一种流行技术。然而，GCF的二分邻接矩阵定义了基于用户-项目交互聚集的邻居，对于交互丰富的用户/项目可能会有噪声，而对于交互稀少的用户/项目可能会有噪声。此外，邻接矩阵忽略了用户-用户和项目-项目的相关性，这可能会限制聚集的受益邻居的范围。在这项工作中，我们提出了一个新的图邻接矩阵，它结合了用户-用户和项目-项目的相关性，以及一个经过适当设计的用户-项目交互矩阵，它平衡了所有用户之间的交互数量。为此，我们预先训练了一种基于图的推荐方法来获得用户/项目嵌入，然后通过TOP-K抽样增强用户-项目交互矩阵。我们还将对称的用户-用户和项目-项目相关性分量增加到邻接矩阵中。我们的实验表明，增强的用户-项目交互矩阵具有更好的邻域和更低的密度，在基于图的推荐中具有显著的优势。此外，我们还表明，包含用户-用户和项目-项目的相关性可以改善对交互丰富和不足的用户的推荐。
Graph collaborative filtering (GCF) is a popular technique for capturing high-order collaborative signals in recommendation systems. However, GCF's bipartite adjacency matrix, which defines the neighbors being aggregated based on user-item interactions, can be noisy for users/items with abundant interactions and insufficient for users/items with scarce interactions. Additionally, the adjacency matrix ignores user-user and item-item correlations, which can limit the scope of beneficial neighbors being aggregated. In this work, we propose a new graph adjacency matrix that incorporates user-user and item-item correlations, as well as a properly designed user-item interaction matrix that balances the number of interactions across all users. To achieve this, we pre-train a graph-based recommendation method to obtain users/items embeddings, and then enhance the user-item interaction matrix via top-K sampling. We also augment the symmetric user-user and item-item correlation components to the adjacency matrix. Our experiments demonstrate that the enhanced user-item interaction matrix with improved neighbors and lower density leads to significant benefits in graph-based recommendation. Moreover, we show that the inclusion of user-user and item-item correlations can improve recommendations for users with both abundant and insufficient interactions.