中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 多媒体计算与图形学团队
MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering

文献类型：期刊论文

作者Hu, Jun1; Hooi, Bryan1; Qian, Shengsheng2; Fang, Quan3; Xu, Changsheng2
刊名IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
出版日期2024-07-01
卷号36期号:7页码:3281-3296
关键词Context modeling Graph neural networks Markov processes Collaborative filtering Neural networks Task analysis Optimization collaborative filtering recommendation systems
ISSN号1041-4347
DOI10.1109/TKDE.2023.3348537
通讯作者Hooi, Bryan(bhooi@comp.nus.edu.sg)
英文摘要Graph Neural Networks (GNNs) have recently been utilized to build Collaborative Filtering (CF) models to predict user preferences based on historical user-item interactions. However, there is relatively little understanding of how GNN-based CF models relate to some traditional Network Representation Learning (NRL) approaches. In this paper, we show the equivalence between some state-of-the-art GNN-based CF models and a traditional 1-layer NRL model based on context encoding. Based on a Markov process that trades off two types of distances, we present Markov Graph Diffusion Collaborative Filtering (MGDCF) to generalize some state-of-the-art GNN-based CF models. Instead of considering the GNN as a trainable black box that propagates learnable user/item vertex embeddings, we treat GNNs as an untrainable Markov process that can construct constant context features of vertices for a traditional NRL model that encodes context features with a fully-connected layer. Such simplification can help us to better understand how GNNs benefit CF models. Especially, it helps us realize that ranking losses play crucial roles in GNN-based CF tasks. With our proposed simple yet powerful ranking loss InfoBPR, the NRL model can still perform well without the context features constructed by GNNs. We conduct experiments to perform detailed analysis on MGDCF.
资助项目National Research Foundation Singapore
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001245017200009
出版者IEEE COMPUTER SOC
资助机构National Research Foundation Singapore
源URL[http://ir.ia.ac.cn/handle/173211/59100]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者Hooi, Bryan
作者单位1.Natl Univ Singapore, Sch Comp, Singapore 119077, Singapore
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100045, Peoples R China
3.Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Beijing 100876, Peoples R China
推荐引用方式
GB/T 7714		 Hu, Jun,Hooi, Bryan,Qian, Shengsheng,et al. MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2024,36(7):3281-3296.
APA Hu, Jun,Hooi, Bryan,Qian, Shengsheng,Fang, Quan,&Xu, Changsheng.(2024).MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,36(7),3281-3296.
MLA Hu, Jun,et al."MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 36.7(2024):3281-3296.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。