层次和对比表示学习应用于知识感知推荐（英文版）

英文标题：Hierarchical and Contrastive Representation Learning for Knowledge-aware Recommendation中文摘要：提出了一种面向知识感知推荐的层次化和对比的表示学习框架 HiCON，其中包括层次化消息聚合机制和跨序对比学习，实验表明 HiCON 对现有方法具有显着的优势。英文摘要：Incorporating knowledge graph into recommendation is an effective way toalleviate data sparsity. Most existing knowledge-aware methods usually performrecursive embedding propagation by enumerating graph neighbors. However, thenumber of nodes' neighbors grows exponentially as the hop number increases,forcing the nodes