logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Deep maximum margin matrix factorization

delete2026-03-22
delete0
delete
OA
AI
S
Shailendra Kumar *
V
Venkateswara Rao Kagita *
V
Vikas Kumar
G
Gaurav Niranjan
DOI：10.1038/s41598-026-44839-0delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
协同过滤（CF）在序数反馈上的应用自然地被组织为一个矩阵补全问题，其中输入由一个部分观测到的用户-物品交互矩阵组成。最大间隔矩阵分解（MMMF）自问世以来，因其能够有效地补全此类部分观测的序数矩阵而广受欢迎。从几何学角度看，MMMF将物品嵌入为点，用户嵌入为线性超平面，以区分具有相似评分的物品与其他物品。全阈值合页损失函数确保用户超平面最大化不同评分类别物品之间的间隔。然而，用户超平面必须为线性的限制显著制约了MMMF的性能，因为用户特征通常复杂且不呈现线性模式。为解决此问题，我们提出了最大间隔矩阵分解的深度变体，该变体可通过适应复杂的非线性用户品味和物品特征表示，轻松预测用户-物品交互。我们通过在三个基准数据集上的实验表明，所提出的MMMF深度变体在归一化平均绝对误差（NMAE）指标上优于各种最先进的CF方法。
Keyword:
Engineering
Mathematics and computing
Collaborative filtering
Deep learning
Deep MMMF
Recommender systems
Science
Humanities and Social Sciences
multidisciplinary
AI总结

AI总结

对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Scientific Reports 封面图
Scientific Reports
IF:
3.9
论文数:
27.8W
被引数:
83.5W

机构

U
University of Delhi
学者数:
638
论文数: 338
被引数: 5
N
national institute of technology
学者数:
741
论文数: 407
被引数: 1
U
university of tubingen
学者数:
509
论文数: 188
被引数: 0
学者 查看更多机构
引用论文

引用论文

Deep learning techniques for recommender systems based on collaborative filtering
errEXPERT SYSTEMS
IF2.3
err2020-11-14
err133
PREAI
errMartins, Guilherme Brandao; Papa, Joao Paulo; Adeli, Hojjat
err分享
err收藏
Recommender system application developments: A survey
errDECISION SUPPORT SYSTEMS
IF6.8
err2015-06-01
err1.1K
errOAAI
errLu, Jie; Wu, Dianshuang; Mao, Mingsong; Wang, Wei; Zhang, Guangquan
err分享
err收藏
Deep Learning Architecture for Collaborative Filtering Recommender Systems
errApplied Sciences
IF0
err2020-04-03
err0
errOAAI
errJesus Bobadilla; Santiago Alonso; Antonio Hernando
err分享
err收藏
Fast maximum margin matrix factorization for collaborative prediction
errProceedings of the 22nd international conference on Machine learning - ICML '05
IF0
err2005-01-01
err0
PREAI
errJasson D. M. Rennie; Nathan Srebro
err分享
err收藏
Deep Matrix Factorization Approach for Collaborative Filtering Recommender Systems
errApplied Sciences
IF0
err2020-07-17
err0
errOAAI
errRaúl Lara-Cabrera; Ángel González-Prieto; Fernando Ortega
err分享
err收藏
Regularizing Matrix Factorization with User and Item Embeddings for Recommendation
errProceedings of the 27th ACM International Conference on Information and Knowledge Management
IF0
err2018-10-17
err0
errOAAI
errThanh Tran; Kyumin Lee; Yiming Liao; Dongwon Lee
err分享
err收藏
Dual-regularized matrix factorization with deep neural networks for recommender systems推荐系统中基于深度神经网络的双正则矩阵分解
errKNOWLEDGE-BASED SYSTEMS
IF7.6
err2018-04-01
err105
PREAI
errWu, Hao; Zhang, Zhengxin; Yue, Kun; Zhang, Binbin; He, Jun; Sun, Liangchen
err分享
err收藏
AutoRec
errProceedings of the 24th International Conference on World Wide Web
IF0
err2015-05-18
err0
PREAI
errSuvash Sedhain; Aditya Krishna Menon; Scott Sanner; Lexing Xie
err分享
err收藏
Proximal maximum margin matrix factorization for collaborative filtering
errPATTERN RECOGNITION LETTERS
IF3.3
err2017-01-01
err26
PREAI
errKumar, Vikas; Pujari, Arun K.; Sahu, Sandeep Kumar; Kagita, Venkateswara Rao; Padmanabhan, Vineet
err分享
err收藏
Collaborative Deep Learning for Recommender Systems
errProceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
IF0
err2015-08-10
err0
errOAAI
errHao Wang; Naiyan Wang; Dit-Yan Yeung
err分享
err收藏
学者 查看更多内容