Liu Weiwen, Zhang Yin, Wang Jianling, He Yun, Caverlee James, Chan Patrick P K, Yeung Daniel S, Heng Pheng-Ann
IEEE Trans Neural Netw Learn Syst. 2022 Sep;33(9):4785-4799. doi: 10.1109/TNNLS.2021.3060872. Epub 2022 Aug 31.
In a modern e-commerce recommender system, it is important to understand the relationships among products. Recognizing product relationships-such as complements or substitutes-accurately is an essential task for generating better recommendation results, as well as improving explainability in recommendation. Products and their associated relationships naturally form a product graph, yet existing efforts do not fully exploit the product graph's topological structure. They usually only consider the information from directly connected products. In fact, the connectivity of products a few hops away also contains rich semantics and could be utilized for improved relationship prediction. In this work, we formulate the problem as a multilabel link prediction task and propose a novel graph neural network-based framework, item relationship graph neural network (IRGNN), for discovering multiple complex relationships simultaneously. We incorporate multihop relationships of products by recursively updating node embeddings using the messages from their neighbors. An edge relational network is designed to effectively capture relational information between products. Extensive experiments are conducted on real-world product data, validating the effectiveness of IRGNN, especially on large and sparse product graphs.
在现代电子商务推荐系统中，理解产品之间的关系非常重要。准确识别产品关系（如互补品或替代品）是生成更好的推荐结果以及提高推荐可解释性的一项基本任务。产品及其关联关系自然地形成了一个产品图，但现有的工作并未充分利用产品图的拓扑结构。它们通常只考虑直接相连产品的信息。实际上，相隔几步的产品之间的连通性也包含丰富的语义信息，可用于改进关系预测。在这项工作中，我们将该问题表述为一个多标签链接预测任务，并提出了一种基于图神经网络的新颖框架——商品关系图神经网络（IRGNN），用于同时发现多种复杂关系。我们通过使用来自邻居的消息递归更新节点嵌入来纳入产品的多跳关系。设计了一个边关系网络来有效捕捉产品之间的关系信息。在真实世界的产品数据上进行了大量实验，验证了IRGNN的有效性，特别是在大型稀疏产品图上。
