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 2007.00216cs.IR
收藏

基于邻域的异构图推荐交互模型

An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph

Jiarui Jin, Jiarui Qin, Yuchen Fang, Kounianhua Du, Weinan Zhang, Yong Yu, Zheng Zhang, Alexander J. Smola

摘要:

由于异构信息网络(HIN)能够描述复杂的图形,并包含丰富的语义,近年来出现了大量基于HIN的推荐系统。虽然现有的方法已经实现了性能改进,但在实用的同时,它们仍然面临以下问题。一方面,大多数现有的基于HIN的方法依赖于显式路径可达性来利用用户和项目之间的基于路径的语义相关性,例如,基于隐喻的相似性这些方法很难使用和集成,因为路径连接是稀疏或嘈杂的,并且通常具有不同的长度。另一方面,其他基于图的方法旨在通过在预测之前将节点及其邻域信息压缩到单个嵌入中来学习有效的异构网络表示。这种弱耦合的建模方式忽略了节点之间丰富的交互,这引入了早期摘要问题。针对上述问题,本文提出了一种端到端的基于邻居的交互推荐模型(NIRec)。具体来说,我们首先分析了在HIN中学习交互的意义,然后提出了一种新的配方,以捕捉每对节点之间的交互模式,通过他们的元路径引导的邻居。然后,为了探索元路径之间的复杂交互并处理大规模网络上的学习复杂性,我们以卷积方式表达交互,并使用快速傅立叶变换进行有效学习。在四种不同类型的异构图上进行的大量实验表明,与现有技术相比,NIRec的性能有所提高。据我们所知,这是第一个工作提供了一个有效的基于邻里的互动模型在基于HIN的建议。

英文摘要:

There is an influx of heterogeneous information network (HIN) based recommender systems in recent years since HIN is capable of characterizing complex graphs and contains rich semantics. Although the existing approaches have achieved performance improvement, while practical, they still face the following problems. On one hand, most existing HIN-based methods rely on explicit path reachability to leverage path-based semantic relatedness between users and items, e.g., metapath-based similarities. These methods are hard to use and integrate since path connections are sparse or noisy, and are often of different lengths. On the other hand, other graph-based methods aim to learn effective heterogeneous network representations by compressing node together with its neighborhood information into single embedding before prediction. This weakly coupled manner in modeling overlooks the rich interactions among nodes, which introduces an early summarization issue. In this paper, we propose an end-to-end Neighborhood-based Interaction Model for Recommendation (NIRec) to address the above problems. Specifically, we first analyze the significance of learning interactions in HINs and then propose a novel formulation to capture the interactive patterns between each pair of nodes through their metapath-guided neighborhoods. Then, to explore complex interactions between metapaths and deal with the learning complexity on large-scale networks, we formulate interaction in a convolutional way and learn efficiently with fast Fourier transform. The extensive experiments on four different types of heterogeneous graphs demonstrate the performance gains of NIRec comparing with state-of-the-arts. To the best of our knowledge, this is the first work providing an efficient neighborhood-based interaction model in the HIN-based recommendations.

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。

↑