Graph-Theoretic Insights into Bayesian Personalized Ranking for Recommendation
Kai Zheng, Jianxin Wang, Jinhui Xu
摘要
Graph self-supervised learning (GSL) is essential for processing graph-structured data, reducing the need for manual labeling. Traditionally, this paradigm has extensively utilized Bayesian Personalized Ranking (BPR) as its primary loss function. Despite its widespread application, the theoretical analysis of its node relations evaluation have remained largely unexplored. This paper employs recent advancements in latent hyperbolic geometry to deepen our understanding of node relationships from a graph-theoretical perspective. We analyze BPR's limitations, particularly its reliance on local connectivity through 2-hop paths, which overlooks global connectivity and the broader topological structure. To address these shortcomings, we purpose a novel loss function, BPR+, designed to encompass even-hop paths and better capture global connectivity and topological nuances. This approach facilitates a more detailed measurement of user-item relationships and improves the granularity of relationship assessments. We validate BPR+ through extensive empirical testing across five real-world datasets and demonstrate its efficacy in refining graph self-supervised learning frameworks. Additionally, we explore the application of BPR+ in drug repositioning, highlighting its potential to support pharmaceutical research and development. Our findings not only illuminate the success factors of previous methodologies but also offer new theoretical insights into this learning paradigm.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
脉络
- Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning 引用了 LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
- Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning 引用了 Self-supervised Graph Learning for Recommendation
- LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation 引用了 Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning
- LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation 引用了 LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
- LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation 引用了 Self-supervised Graph Learning for Recommendation
- Self-supervised Graph Learning for Recommendation 引用了 LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
- Self-supervised Graph Learning for Recommendation 引用了 Momentum Contrast for Unsupervised Visual Representation Learning
它引用的 Paper5
- LightGCN: Simplifying and Powering Graph Convolution Network for RecommendationXiangnan He, Kuan Deng, Xiang Wang, Yan Li 等SIGIR 2020 · 4,448 次引用
- Self-supervised Graph Learning for RecommendationJiancan Wu, Xiang Wang, Fuli Feng, Xiangnan He 等SIGIR 2021 · 1,476 次引用
- Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive LearningZihan Lin, Changxin Tian, Yupeng Hou, Wayne Xin ZhaoWWW 2022 · 606 次引用
- LightGCL: Simple Yet Effective Graph Contrastive Learning for RecommendationXuheng Cai, Chao Huang, Lianghao Xia, Xubin RenICLR 2023 · 99 次引用
- Momentum Contrast for Unsupervised Visual Representation LearningKaiming He, Haoqi Fan, Yuxin Wu, Saining Xie 等CVPR 2020
相关 Paper
- Pre-training Molecular Graph Representation with 3D GeometryShengchao Liu, Hanchen Wang, Weiyang Liu, Joan Lasenby 等ICLR 2022 · 440 次引用
- Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge GraphsNurendra Choudhary, Nikhil Rao, Sumeet Katariya, Karthik Subbian 等WWW 2021 · 73 次引用
- HyperGC: Learning Hypergraph Representations via Full Hyperedge Reconstruction and Contrastive EvaluationDavid Yoon Suk Kang, So-Bin Jung, Sang-Wook KimKDD 2026
- Hypergraph Contrastive Collaborative FilteringLianghao Xia, Chao Huang, Yong Xu, Jiashu Zhao 等SIGIR 2022 · 445 次引用
- Link Prediction with Non-Contrastive LearningWilliam Shiao, Zhichun Guo, Tong Zhao, Evangelos E. Papalexakis 等ICLR 2023 · 5 次引用
