2019/05/31 by Xiang Wang, Xiangnan He, Meng Wang +2 · 15 citations
Computer Science · #Advanced Graph Neural Networks #Collaborative filtering #Core (optical fiber) #Data Visualization and Analytics #Embedding #Feature learning #Graph #Matrix decomposition #Ranging #Recommender Systems and Techniques #Recommender system #cs.IR #cs.LG #cs.SI
paper · pdf · doi:10.1145/3331184.3331267
SIGIR 2019; the latest version of NGCF paper, which is distinct from the version published in ACM Digital Library
openalex created_date 2019/05/29 · openalex publication_date 2019/07/18 · arxiv created 2020/07/03 · arxiv updated 2020/07/06 · openalex updated_date 2026/08/05
Learning vector representations (aka. embeddings) of users and items lies at the core of modern recommender systems. Ranging from early matrix factorization to recently emerged deep learning based methods, existing efforts typically obtain a user's (or an item's) embedding by mapping from pre-existing features that describe the user (or the item), such as ID and attributes. We argue that an inherent drawback of such methods is that, the collaborative signal, which is latent in user-item interactions, is not encoded in the embedding process. As such, the resultant embeddings may not be sufficient to capture the collaborative filtering effect.