Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xu, Cong, Wang, Jun, Wang, Jianyong, Zhang, Wei
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929516376489984
author Xu, Cong
Wang, Jun
Wang, Jianyong
Zhang, Wei
author_facet Xu, Cong
Wang, Jun
Wang, Jianyong
Zhang, Wei
contents Embedding plays a key role in modern recommender systems because they are virtual representations of real-world entities and the foundation for subsequent decision-making 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 module, SEvo is able to directly inject graph structural information into embedding with minimal computational overhead during training. The convergence properties of SEvo along with its potential variants are theoretically analyzed to justify the validity of the designs. Moreover, SEvo can be seamlessly integrated into existing optimizers for state-of-the-art performance. Particularly SEvo-enhanced AdamW with moment estimate correction demonstrates consistent improvements across a spectrum of models and datasets, suggesting a novel technical route to effectively utilize graph structural information beyond explicit GNN modules.
format Preprint
id arxiv_https___arxiv_org_abs_2310_03032
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution
Xu, Cong
Wang, Jun
Wang, Jianyong
Zhang, Wei
Information Retrieval
Machine Learning
Embedding plays a key role in modern recommender systems because they are virtual representations of real-world entities and the foundation for subsequent decision-making 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 module, SEvo is able to directly inject graph structural information into embedding with minimal computational overhead during training. The convergence properties of SEvo along with its potential variants are theoretically analyzed to justify the validity of the designs. Moreover, SEvo can be seamlessly integrated into existing optimizers for state-of-the-art performance. Particularly SEvo-enhanced AdamW with moment estimate correction demonstrates consistent improvements across a spectrum of models and datasets, suggesting a novel technical route to effectively utilize graph structural information beyond explicit GNN modules.
title Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2310.03032