| 摘要: |
| 近年来, 基于图神经网络(graph neural network, GNN)的推荐系统能够很好地利用交互数据的交互结构来学习用户和项目表示. 然而, 现有的基于图神经网络的推荐模型在聚合过程中往往忽略了交互的时态信息, 从而难以建模用户兴趣变化特征, 导致推荐模型对数据产生过度拟合, 造成推荐结果缺乏多样性, 难以满足用户更加多样化的需求. 针对上述问题, 提出了一种时态信息增强的多样化推荐模型. 首先, 利用注意力机制来捕获历史用户-物品交互中的时态信息和交互结构信息并融合. 同时, 为降低特征冗余并提高表示辨识度, 设计了特征分离模块, 将平滑的全局特征与突出且具有判别力的关键信号进行解耦. 然后, 通过邻居选择来突出节点间的差异并进行图卷积, 利用层注意力机制来缓解过平滑问题. 最后, 通过重加权损失增强对长尾类别项目的学习以增强多样性. 通过在两个数据集上的大量实验验证, 结果表明所提方法可以在实现最佳多样性的同时, 保持较高的准确性. |
| 关键词: 图神经网络 推荐系统 多样性 时态信息 深度学习 表示学习 |
| DOI：10.13328/j.cnki.jos.007577 |
| 分类号:TP18 |
| 基金项目:中央高校基本科研业务费专项资金(2024-10949); 江苏省研究生科研与实践创新计划 (KYCX24_2781); 徐州市重点研发计划(KC23296); 徐州市科技基金(KC22047); 中国矿业大学研究生创新计划 (2024WLKXJ183) |
|
| Temporal-information-enhanced Diversified Recommendation Algorithm |
|
YUAN Guan1,2, ZENG Xiang-Yu1, ZHANG Gui-Xian1, ZHANG Yan-Mei1, ZHANG Yu-Hang1, YANG Pei-Jin1
|
|
1.School of Computer Science and Technology/School of Artificial Intelligence, China University of Mining and Technology, Xuzhou 221116, China;2.Mine Digitization Engineering Research Center of the Ministry of Education (China University of Mining and Technology), Xuzhou 221116, China
|
| Abstract: |
| In recent years, recommender systems based on graph neural network (GNN) have made good use of the interaction structure of interaction data to learn user and item representations. However, existing recommendation models based on GNN often ignore the temporal information of interactions during aggregation, which makes it difficult to model the change characteristics of users’ interests. As a result, this causes overfitting of the recommendation model to data, and a lack of diversity in the recommendation results, thereby making it difficult to satisfy the more diversified needs of users. To this end, a temporal information-enhanced diversified recommendation model is proposed. First, an attention mechanism is employed to capture and fuse temporal information and interaction information from historical user-item interactions. Meanwhile, a feature disentanglement module is designed to disentangle smoothed global features from salient, highly discriminative key signals to reduce feature redundancy and improve representational clarity. Subsequently, neighbour selection is adopted to highlight inter-node differences and conduct graph convolution, with a layer attention mechanism employed to alleviate over smoothing. Finally, the learning of items in the long-tail category is enhanced by reweighting loss to improve the diversity. |
| Key words: graph neural network (GNN) recommender system diversity temporal information deep learning representation learning |
