期刊
PATTERN RECOGNITION
卷 139, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2023.109504
关键词
Sequential Recommendation; Graph Neural Networks; Self-attention Networks; Graph Embedding
Graph neural networks (GNNs) have been widely used in recommendation systems due to their advantages in graph representation learning, and many successful models have applied graph-based methods for sequential recommendation. However, existing research only considers the number of interactions between items, neglecting the multi-dimensional transformation relationships. Therefore, we propose a Category and Time information integrated Graph Neural Network (CT-GNN) that combines item category and interaction time information to form fine-grained item representations, and design a temporal self-attention network for dynamic user preference modeling and next-item recommendation. Experimental results on real-world datasets demonstrate the excellent performance of the proposed model. (c) 2023 Elsevier Ltd. All rights reserved.
Graph neural networks (GNNs) technology has been widely used in recommendation systems because most information in recommendation systems has a graph structure in nature, and GNNs have advan-tages in graph representation learning. In sequential recommendation, the relationships between inter-acting items can be constructed as an isomorphic graph, and (GNNs) can capture high-order information between graph nodes. Many models have used graph-based methods for sequential recommendation, and achieved great success. However, the existing research only considers the number of interactions between items when constructing the item graph. As such, revisions are needed to capture the multi-dimensional transformation relationships between items. Hence, we emphasize the importance of multi-dimensional information, and we propose a Category and Time information integrated Graph Neural Network (CT-GNN), which combines the item category and interaction time information with a multi-layer graph con-volution network to form multi-dimensional fine-grained item representations. In addition, we design a temporal self-attention network to model the dynamic user preference and make the next-item rec-ommendation. Finally, we conduct extensive experiments on three real-world datasets, and the results demonstrate the excellent performance of the proposed model.(c) 2023 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据