JSCN: Joint Spectral Convolutional Network for Cross Domain Recommendation
JSCN: Joint Spectral Convolutional Network for Cross Domain Recommendation
复制标题
DOI：
10.1109/bigdata47090.2019.9006266
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Zhiwei Liu;Lei Zheng;Jiawei Zhang;Jiayu Han;Philip S. Yu
中科院分区：
文献类型：
--
作者：
Zhiwei Liu;Lei Zheng;Jiawei Zhang;Jiayu Han;Philip S. Yu
跨域推荐可以缓解推荐系统中的数据稀疏问题。为了将知识从一个领域转移到另一个领域，可以利用邻域信息或学习直接映射函数。然而，所有现有方法都忽略了跨域推荐区域的高阶连接信息，并且存在域不兼容问题。在本文中，我们提出了一种用于跨域推荐的联合谱卷积网络（JSCN）。 JSCN 将在不同的图上同时操作多层谱卷积，并与域自适应用户映射模块共同学习域不变的用户表示。因此，可以通过谱卷积提取高阶综合连通性信息，并且可以通过域不变的用户映射跨域传输信息。领域自适应用户映射模块可以帮助不兼容的领域相互转移知识。在 24 个亚马逊评级数据集上进行的大量实验表明，JSCN 在跨域推荐方面的有效性，与最先进的方法相比，召回率提高了 9.2%，MAP 提高了 36.4%。我们的代码可以在线获取1.1https://github.com/JimLiu96/JSCN
Cross-domain recommendation can alleviate the data sparsity problem in recommender systems. To transfer the knowledge from one domain to another, one can either utilize the neighborhood information or learn a direct mapping function. However, all existing methods ignore the high-order connectivity information in cross-domain recommendation area and suffer from the domain-incompatibility problem. In this paper, we propose a Joint Spectral Convolutional Network (JSCN) for cross-domain recommendation. JSCN will simultaneously operate multi-layer spectral convolutions on different graphs, and jointly learn a domain-invariant user representation with a domain adaptive user mapping module. As a result, the high-order comprehensive connectivity information can be extracted by the spectral convolutions and the information can be transferred across domains with the domain-invariant user mapping. The domain adaptive user mapping module can help the incompatible domains to transfer the knowledge across each other. Extensive experiments on 24 Amazon rating datasets show the effectiveness of JSCN in the cross-domain recommendation, with 9.2% improvement on recall and 36.4% improvement on MAP compared with state-of-the-art methods. Our code is available online 1.1https://github.com/JimLiu96/JSCN