arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.07057cs.IRcs.AI
收藏

基于知识图谱的推荐交互背后的学习意图

Learning Intents behind Interactions with Knowledge Graph for Recommendation

National University of Singapore(新加坡国立大学);Zhejiang University(浙江大学);eBay(易贝);The Hong Kong Polytechnic University(香港理工大学);University of Science and Technology of China(中国科学技术大学)

Xiang Wang, Tinglin Huang, Dingxian Wang, Yancheng Yuan, Zhenguang Liu, Xiangnan He, Tat-Seng Chua

摘要:

知识图谱在推荐系统中扮演着越来越重要的角色。最近的技术趋势是开发基于图神经网络(GNN)的端到端模型。然而,现有的基于GNN的模型在关系建模中是粗粒度的,未能(1)在细粒度的意图级别识别用户-项目关系,以及(2)利用关系依赖性来保留长距离连接的语义。在这项研究中,我们通过使用辅助项目知识来探索用户-项目交互背后的意图,并提出了一个新的模型,知识图谱-基于意图网络(KGIN)。从技术上讲,我们将每个意图建模为KG关系的精心组合,鼓励不同意图的独立性,以获得更好的模型能力和可解释性。此外,我们设计了一种新的GNN信息聚合方案,它递归地整合了长距离连接的关系序列(即,关系路径)。该方案允许我们提取有关用户意图的有用信息,并将其编码为用户和项目的表示。在三个基准数据集上的实验结果表明,KGIN与KGAT,KGNN-LS和CKAN等最先进的方法相比取得了显着的改进。进一步的分析表明,KGIN通过识别有影响力的意图和关系路径,为预测提供了可解释的解释。这些实现可在https://github.com/huangtinglin/Knowledge_Graph_based_Intent_Network上获得。

英文摘要:

Knowledge graph (KG) plays an increasingly important role in recommender systems. A recent technical trend is to develop end-to-end models founded on graph neural networks (GNNs). However, existing GNN-based models are coarse-grained in relational modeling, failing to (1) identify user-item relation at a fine-grained level of intents, and (2) exploit relation dependencies to preserve the semantics of long-range connectivity. In this study, we explore intents behind a user-item interaction by using auxiliary item knowledge, and propose a new model, Knowledge Graph-based Intent Network (KGIN). Technically, we model each intent as an attentive combination of KG relations, encouraging the independence of different intents for better model capability and interpretability. Furthermore, we devise a new information aggregation scheme for GNN, which recursively integrates the relation sequences of long-range connectivity (i.e., relational paths). This scheme allows us to distill useful information about user intents and encode them into the representations of users and items. Experimental results on three benchmark datasets show that, KGIN achieves significant improvements over the state-of-the-art methods like KGAT, KGNN-LS, and CKAN. Further analyses show that KGIN offers interpretable explanations for predictions by identifying influential intents and relational paths. The implementations are available at https://github.com/huangtinglin/Knowledge_Graph_based_Intent_Network.

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。

↑