arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.04413cs.LGcs.IRstat.ML
收藏

基于标签平滑正则化的知识感知图神经网络推荐系统

Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems

Stanford University(斯坦福大学);Meituan-Dianping Group(美团点评集团);Hong Kong Polytechnic University(香港理工大学)

Hongwei Wang, Fuzheng Zhang, Mengdi Zhang, Jure Leskovec, Miao Zhao, Wenjie Li, Zhongyuan Wang

摘要:

知识图谱捕获一组实体或项目之间的结构化信息和关系。因此,知识图谱代表了一个有吸引力的信息源,可以帮助改善推荐系统。然而,该领域中的现有方法依赖于手动特征工程,并且不允许端到端训练。在这里,我们提出了知识感知的图神经网络与标签平滑正则化(KGNN-LS),以提供更好的建议。从概念上讲,我们的方法计算用户特定的项目嵌入,首先应用一个可训练的功能,确定重要的知识图谱的关系,为给定的用户。通过这种方式,我们将知识图谱转换为用户特定的加权图,然后应用图神经网络来计算个性化的项目嵌入。为了提供更好的归纳偏差,我们依赖于标签平滑性假设,该假设假定知识图谱中的相邻项可能具有相似的用户相关性标签/分数。标签平滑提供了正则化的边缘权重,我们证明了它是等价于一个标签传播计划的图。我们还开发了一个高效的实现,表现出强大的可扩展性方面的知识图谱的大小。在四个数据集上的实验表明,我们的方法优于最先进的基线。KGNN-LS还在用户-项目交互稀疏的冷启动场景中实现了强大的性能。

英文摘要:

Knowledge graphs capture structured information and relations between a set of entities or items. As such knowledge graphs represent an attractive source of information that could help improve recommender systems. However, existing approaches in this domain rely on manual feature engineering and do not allow for an end-to-end training. Here we propose Knowledge-aware Graph Neural Networks with Label Smoothness regularization (KGNN-LS) to provide better recommendations. Conceptually, our approach computes user-specific item embeddings by first applying a trainable function that identifies important knowledge graph relationships for a given user. This way we transform the knowledge graph into a user-specific weighted graph and then apply a graph neural network to compute personalized item embeddings. To provide better inductive bias, we rely on label smoothness assumption, which posits that adjacent items in the knowledge graph are likely to have similar user relevance labels/scores. Label smoothness provides regularization over the edge weights and we prove that it is equivalent to a label propagation scheme on a graph. We also develop an efficient implementation that shows strong scalability with respect to the knowledge graph size. Experiments on four datasets show that our method outperforms state of the art baselines. KGNN-LS also achieves strong performance in cold-start scenarios where user-item interactions are sparse.

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。

↑