Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution

arXiv:2310.03032v2 Announce Type: replace-cross
Abstract: Embedding plays a critical role in modern recommender systems because they are virtual representations of real-world entities and the foundation for subsequent decision models. In this paper, we propose a novel embedding update mechanism, Structure-aware Embedding Evolution (SEvo for short), to encourage related nodes to evolve similarly at each step. Unlike GNN (Graph Neural Network) that typically serves as an intermediate part, SEvo is able to directly inject the graph structure information into embedding with …

abstract arxiv cs.ir cs.lg decision embedding evolution foundation graph modern nodes novel paper recommendation recommender systems role systems type update virtual world