Ripple Knowledge Graph Convolutional Networks For Recommendation Systems

arXiv:2305.01147v2 Announce Type: replace-cross
Abstract: Using knowledge graphs to assist deep learning models in making recommendation decisions has recently been proven to effectively improve the model's interpretability and accuracy. This paper introduces an end-to-end deep learning model, named RKGCN, which dynamically analyses each user's preferences and makes a recommendation of suitable items. It combines knowledge graphs on both the item side and user side to enrich their representations to maximize the utilization of the abundant information in knowledge graphs. RKGCN …

abstract accuracy arxiv cs.ai cs.ir cs.lg decisions deep learning graph graphs interpretability knowledge knowledge graph knowledge graphs making networks paper recommendation recommendation systems ripple systems type