期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 -, 期 -, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2022.3175772
关键词
Recommender systems; Bipartite graph; Business process re-engineering; Graph neural networks; Sparse matrices; Optimization; Negative feedback; Bayesian personalized ranking (BPR) loss; graph neural network (GNN); network embedding (NE); recommender system; signed bipartite graph
类别
资金
- Institute of Information and Communications Technology Planning and Evaluation (IITP) - Korea Government (MSIT) [2020-0-01441]
- National Research Foundation of Korea (NRF) - Korea Government (MSIT) [2021R1A2C3004345]
- Yonsei University Research Fund [2021-22-0083]
This article presents SiReN, a new sign-aware recommender system based on GNN models. SiReN outperforms state-of-the-art NE-aided recommendation methods by constructing a signed bipartite graph, generating embeddings, and establishing a loss function.
In recent years, many recommender systems using network embedding (NE) such as graph neural networks (GNNs) have been extensively studied in the sense of improving recommendation accuracy. However, such attempts have focused mostly on utilizing only the information of positive user-item interactions with high ratings. Thus, there is a challenge on how to make use of low rating scores for representing users' preferences since low ratings can be still informative in designing NE-based recommender systems. In this study, we present SiReN, a new Sign-aware Recommender system based on GNN models. Specifically, SiReN has three key components: 1) constructing a signed bipartite graph for more precisely representing users' preferences, which is split into two edge-disjoint graphs with positive and negative edges each; 2) generating two embeddings for the partitioned graphs with positive and negative edges via a GNN model and a multilayer perceptron (MLP), respectively, and then using an attention model to obtain the final embeddings; and 3) establishing a sign-aware Bayesian personalized ranking (BPR) loss function in the process of optimization. Through comprehensive experiments, we empirically demonstrate that SiReN consistently outperforms state-of-the-art NE-aided recommendation methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据