Recent advancements in Graph Neural Networks (GNN) have led to the development of Sheaf4Rec, a novel architecture for recommender systems. Sheaf4Rec utilizes Sheaf Neural Networks to provide a more comprehensive representation of users and items, resulting in improved performance across various datasets. The model demonstrates significant improvements in terms of F1-Score@10 and NDCG@10 compared to existing state-of-the-art models like NGCF and KGTORe. Additionally, Sheaf4Rec shows efficiency gains in recommendation computation, with substantial runtime improvements ranging from 2.5% up to 37% when compared to other GNN-based competitor models.
To Another Language
from source content
arxiv.org
สอบถามเพิ่มเติม