DAN：一种用于个性化推荐的深度联合神经网络

王旭娜; 谭清美

doi:10.1631/FITEE.1900236

Your Location：

Home >

Browse articles >

DAN：一种用于个性化推荐的深度联合神经网络

常规文章 | Updated：2022-05-19

- DAN：一种用于个性化推荐的深度联合神经网络
- DAN: a deep association neural network approach for personalization recommendation
- 信息与电子工程前沿（英文） 2020年21卷第7期页码：963-980
- Affiliations：
  
  College of Economic and Management, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
- Author bio：
  
  [ "Xu-na WANG, E-mail: Xuna@nuaa.edu.cn" ]
  Qing-mei TAN, E-mail: tanchina@nuaa.edu.cn
- Funds：
  
  Project supported by the National Social Science Foundation of China (No. 19AGL003)
- DOI：10.1631/FITEE.1900236
  中图分类号： TP391
- 收稿：2019-05-10，
  
  修回：2020-;6-22，
  
  纸质出版：2020-07
- Accepted：
Scan QR Code
王旭娜, 谭清美. DAN：一种用于个性化推荐的深度联合神经网络[J]. 信息与电子工程前沿（英文）, 2020,21(7):963-980.

Xu-na WANG, Qing-mei TAN. DAN: a deep association neural network approach for personalization recommendation[J]. Frontiers of Information Technology & Electronic Engineering, 2020, 21(7): 963-980.
王旭娜, 谭清美. DAN：一种用于个性化推荐的深度联合神经网络[J]. 信息与电子工程前沿（英文）, 2020,21(7):963-980. DOI： 10.1631/FITEE.1900236.

Xu-na WANG, Qing-mei TAN. DAN: a deep association neural network approach for personalization recommendation[J]. Frontiers of Information Technology & Electronic Engineering, 2020, 21(7): 963-980. DOI： 10.1631/FITEE.1900236.

摘要

传统推荐系统采用的协同过滤技术存在数据稀疏问题，同时传统的矩阵分解算法简单地将用户和项目分解为潜在因素的线性模型，这些局限性导致传统推荐算法推荐效果有限。在此情况下，出现了基于深度学习的推荐系统。当前深度学习推荐大多利用深度神经网络针对一些辅助信息建模，且在建模过程中根据输入数据类别，分别采用多条映射通路，将原始输入数据映射到潜在向量空间。然而，这些深度神经网络推荐算法忽略了不同类别数据间的联合作用可能对推荐效果产生的潜在影响。针对这一问题，本文提出一种基于多类别信息联合作用的前馈深度神经网络推荐方法--深度联合网络，以解决隐性反馈的推荐问题。具体来说，一方面，本文研究在模型的底层输入中不仅包含用户和项目信息，而且包含更多辅助信息。另一方面，充分考虑不同类别信息的联合作用对推荐效果的影响。在公开数据集上的实验表明，我们提出的方法对现有方法有显著改进。经验证据表明，使用深度联合推荐可以提供更好推荐性能。

Abstract

The collaborative filtering technology used in traditional recommendation systems has a problem of data sparsity. The traditional matrix decomposition algorithm simply decomposes users and items into a linear model of potential factors. These limitations have led to the low accuracy in traditional recommendation algorithms

thus leading to the emergence of recommendation systems based on deep learning. At present

deep learning recommendations mostly use deep neural networks to model some of the auxiliary information

and in the process of modeling

multiple mapping paths are adopted to map the original input data to the potential vector space. However

these deep neural network recommendation algorithms ignore the combined effects of different categories of data

which can have a potential impact on the effectiveness of the recommendation. Aimed at this problem

in this paper we propose a feedforward deep neural network recommendation method

called the deep association neural network (DAN)

which is based on the joint action of multiple categories of information

for implicit feedback recommendation. Specifically

the underlying input of the model includes not only users and items

but also more auxiliary information. In addition

the impact of the joint action of different types of information on the recommendation is considered. Experiments on an open data set show the significant improvements made by our proposed method over the other methods. Empirical evidence shows that deep

joint recommendations can provide better recommendation performance.

关键词

Keywords

references

F Aiolli . . Convex AUC optimization for top- n recommendation with implicit feedback . . Proc 8 th ACM Conf on Recommender Systems , , 2014 . . p.293 - - 296 . . DOI: 10.1145/2645710.2645770 http://doi.org/10.1145/2645710.2645770 . .

O Barkan , , , N Koenigstein . . Item2Vec: neural item embedding for collaborative filtering . . Proc IEEE 26 th Int Workshop on Machine Learning for Signal Processing , , 2016 . . p.1 - - 6 . . DOI: 10.1109/MLSP.2016.7738886 http://doi.org/10.1109/MLSP.2016.7738886 . .

I Bayer , , , XN He , , , B Kanagal , , , 等 . . A generic coordinate descent framework for learning from implicit feedback . . Proc 26 th Int Conf on World Wide Web , , 2017 . . p.1341 - - 1350 . . DOI: 10.1145/3038912.3052694 http://doi.org/10.1145/3038912.3052694 . .

R Buettner . . Predicting user behavior in electronic markets based on personality-mining in large online social networks . . Electron Mark , , 2016 . . 27 ( ( 3 ): ): 247 - - 265 . . DOI: 10.1007/s12525-016-0228-z http://doi.org/10.1007/s12525-016-0228-z . .

YL Cao , , , WL Li , , , DX Zheng . . An improved neighborhood- aware unified probabilistic matrix factorization recommendation . . Wirel Pers Commun , , 2018 . . 102 ( ( 4 ): ): 3121 - - 3140 . . DOI: 10.1007/s11277-018-5332-2 http://doi.org/10.1007/s11277-018-5332-2 . .

G Cheng , , , CY Yang , , , XW Yao , , , 等 . . When deep learning meets metric learning: remote sensing image scene classification via learning discriminative CNNs . . IEEE Trans Geosci Remote Sens , , 2018 . . 56 ( ( 5 ): ): 2811 - - 2821 . . DOI: 10.1109/TGRS.2017.2783902 http://doi.org/10.1109/TGRS.2017.2783902 . .

GM del Corso , , , M Gianna , , , F Romani . . Adaptive nonnegative matrix factorization and measure comparisons for recommender systems . . Appl Math Comput , , 2019 . . 354 164 - - 179 . . DOI: 10.1016/j.amc.2019.01.047 http://doi.org/10.1016/j.amc.2019.01.047 . .

AM Elkahky , , , Y Song , , , XD He . . A multi-view deep learning approach for cross domain user modeling in recommendation systems . . Proc 24 th Int Conf on World Wide Web , , 2015 . . p.278 - - 288 . . DOI: 10.1145/2736277.2741667 http://doi.org/10.1145/2736277.2741667 . .

MS Fu , , , H Qu , , , Z Yi , , , 等 . . A novel deep learning-based collaborative filtering model for recommendation system . . IEEE Trans Cybern , , 2019 . . 49 ( ( 3 ): ): 1084 - - 1096 . . DOI: 10.1109/TCYB.2018.2795041 http://doi.org/10.1109/TCYB.2018.2795041 . .

HF Guo , , , RM Tang , , , YM Ye , , , 等 . . DeepFM: a factorization- machine based neural network for CTR prediction , , 2017 . . https://arxiv.org/abs/1703.04247 https://arxiv.org/abs/1703.04247 , , . .

T Ha , , , S Lee . . Item-network-based collaborative filtering: a personalized recommendation method based on a useros item network . . Inform Process Manag , , 2017 . . 53 ( ( 5 ): ): 1171 - - 1184 . . DOI: 10.1016/j.ipm.2017.05.003 http://doi.org/10.1016/j.ipm.2017.05.003 . .

XN He , , , HW Zhang , , , MY Kan , , , 等 . . Fast matrix factorization for online recommendation with implicit feedback . . Proc 39 th Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2016 . . p.549 - - 558 . . DOI: 10.1145/2911451.2911489 http://doi.org/10.1145/2911451.2911489 . .

XN He , , , LZ Liao , , , HW Zhang , , , 等 . . Neural collaborative filtering . . Proc 26 th Int Conf on World Wide Web , , 2017 . . p.173 - - 182 . . DOI: 10.1145/3038912.3052569 http://doi.org/10.1145/3038912.3052569 . .

XN He , , , XY Du , , , X Wang , , , 等 . . Outer product-based neural collaborative filtering , , 2018 . . https://arxiv.org/abs/1808.03912 https://arxiv.org/abs/1808.03912 , , . .

A Hernando , , , J Bobadilla , , , F Ortega . . A non negative matrix factorization for collaborative filtering recommender systems based on a Bayesian probabilistic model . . Knowl-Based Syst , , 2016 . . 97 188 - - 202 . . DOI: 10.1016/j.knosys.2015.12.018 http://doi.org/10.1016/j.knosys.2015.12.018 . .

MS Hossain , , , G Muhammad . . Emotion recognition using deep learning approach from audio-visual emotional big data . . Inform Fus , , 2018 . . 49 69 - - 78 . . DOI: 10.1016/j.inffus.2018.09.008 http://doi.org/10.1016/j.inffus.2018.09.008 . .

CC Hsu , , , MY Yeh , , , SD Lin . . A general framework for implicit and explicit social recommendation . . IEEE Trans Knowl Data Eng , , 2018 . . 30 ( ( 12 ): ): 2228 - - 2241 . . DOI: 10.1109/TKDE.2018.2821174 http://doi.org/10.1109/TKDE.2018.2821174 . .

XW Jia , , , XY Li , , , L Kang , , , 等 . . Collaborative restricted Boltzmann machine for social event recommendation . . IEEE/ACM Int Conf on Advances in Social Networks Analysis and Mining , , 2016 . . p.402 - - 405 . . DOI: 10.1109/ASONAM.2016.7752265 http://doi.org/10.1109/ASONAM.2016.7752265 . .

JJ Jung . . Attribute selection-based recommendation framework for short-head user group: an empirical study by MovieLens and IMDB . . Expert Syst Appl , , 2012 . . 39 ( ( 4 ): ): 4049 - - 4054 . . DOI: 10.1016/j.eswa.2011.09.096 http://doi.org/10.1016/j.eswa.2011.09.096 . .

J Knoll , , , J Stȹbinger , , , M Grottke . . Exploiting social media with higher-order factorization machines: statistical arbitrage on high-frequency data of the S & P 500 . . Quant Finan , , 2019 . . 19 ( ( 4 ): ): 571 - - 585 . . DOI: 10.1080/14697688.2018.1521002 http://doi.org/10.1080/14697688.2018.1521002 . .

Y Li , , , SH Wang , , , Q Pan , , , 等 . . Learning binary codes with neural collaborative filtering for efficient recommendation systems . . Knowl-Based Syst , , 2019 . . 172 64 - - 75 . . DOI: 10.1016/j.knosys.2019.02.012 http://doi.org/10.1016/j.knosys.2019.02.012 . .

ZC Li , , , JH Tang . . Weakly supervised deep matrix factorization for social image understanding . . IEEE Trans Image Process , , 2017 . . 26 ( ( 1 ): ): 276 - - 288 . . DOI: 10.1109/TIP.2016.2624140 http://doi.org/10.1109/TIP.2016.2624140 . .

JT Liu , , , CH Wu . . Deep learning based recommendation: a survey . . Int Conf on Information Science and Applications , , 2017 . . p.451 - - 458 . . DOI: 10.1007/978-981-10-4154-9_52 http://doi.org/10.1007/978-981-10-4154-9_52 . .

WB Liu , , , ZD Wang , , , XH Liu , , , 等 . . A survey of deep neural network architectures and their applications . . Neurocomputing , , 2017 . . 234 11 - - 26 . . DOI: 10.1016/j.neucom.2016.12.038 http://doi.org/10.1016/j.neucom.2016.12.038 . .

Y Liu , , , LF Li , , , J Liu . . Bilateral neural embedding for collaborative filtering-based multimedia recommendation . . Multim Tools Appl , , 2018 . . 77 ( ( 10 ): ): 12533 - - 12544 . . DOI: 10.1007/s11042-017-4902-8 http://doi.org/10.1007/s11042-017-4902-8 . .

J Lu , , , DS Wu , , , MS Mao , , , 等 . . Recommender system application developments: a survey . . Dec Supp Syst , , 2015 . . 74 12 - - 32 . . DOI: 10.1016/j.dss.2015.03.008 http://doi.org/10.1016/j.dss.2015.03.008 . .

L Luo , , , HR Xie , , , YH Rao , , , 等 . . Personalized recommendation by matrix co-factorization with tags and time information . . Expert Syst Appl , , 2018 . . 119 311 - - 321 . . DOI: 10.1016/j.eswa.2018.11.003 http://doi.org/10.1016/j.eswa.2018.11.003 . .

C Ma , , , YX Zhang , , , QL Wang , , , 等 . . Point-of-interest recommendation: exploiting self-attentive autoencoders with neighbor-aware influence . . Proc 27 th ACM Int Conf on Information and Knowledge Management , , 2018 . . p.697 - - 706 . . DOI: 10.1145/3269206.3271733 http://doi.org/10.1145/3269206.3271733 . .

E Marchi , , , F Vesperini , , , F Eyben , , , 等 . . A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks . . IEEE Int Conf on Acoustics, Speech and Signal Processing , , 2015 . . p.1996 - - 2000 . . DOI: 10.1109/ICASSP.2015.7178320 http://doi.org/10.1109/ICASSP.2015.7178320 . .

K Noda , , , Y Yamaguchi , , , K Nakadai , , , 等 . . Audio-visual speech recognition using deep learning . . Appl Intell , , 2015 . . 42 722 - - 737 . . DOI: 10.1007/s10489-014-0629-7 http://doi.org/10.1007/s10489-014-0629-7 . .

J Pan , , , YY Zi , , , JL Chen , , , 等 . . LiftingNet: a novel deep learning network with layerwise feature learning from noisy mechanical data for fault classification . . IEEE Trans Ind Electron , , 2017 . . 65 ( ( 6 ): ): 4973 - - 4982 . . DOI: 10.1109/TIE.2017.2767540 http://doi.org/10.1109/TIE.2017.2767540 . .

WK Pan , , , L Chen , , , Z Ming . . Personalized recommendation with implicit feedback via learning pairwise preferences over item-sets . . Knowl Inform Syst , , 2019 . . 58 ( ( 2 ): ): 295 - - 318 . . DOI: 10.1007/s10115-018-1154-5 http://doi.org/10.1007/s10115-018-1154-5 . .

K Verstrepen , , , K Bhaduriy , , , B Cule , , , 等 . . Collaborative filtering for binary, positiveonly data . . ACM SIGKDD Explor Newsl , , 2017 . . 19 ( ( 1 ): ): 1 - - 21 . . DOI: 10.1145/3137597.3137599 http://doi.org/10.1145/3137597.3137599 . .

XN Wang , , , QM Tan , , , LF Zhang . . A deep neural network of multi-form alliances for personalized recommendations . . Inform Sci , , 2020 . . 531 68 - - 86 . . DOI: 10.1016/j.ins.2020.03.062 http://doi.org/10.1016/j.ins.2020.03.062 . .

L Wu , , , EH Chen , , , Q Liu , , , 等 . . Leveraging tagging for neighborhood-aware probabilistic matrix factorization . . Proc 21 st ACM Int Conf on Information and Knowledge Management , , 2012 . . p.1854 - - 1858 . . DOI: 10.1145/2396761.2398531 http://doi.org/10.1145/2396761.2398531 . .

YY Xiao , , , GW Wang , , , CH Hsu , , , 等 . . A time-sensitive personalized recommendation method based on probabilistic matrix factorization technique . . Soft Comput , , 2018 . . 22 ( ( 20 ): ): 6785 - - 6796 . . DOI: 10.1007/s00500-018-3406-4 http://doi.org/10.1007/s00500-018-3406-4 . .

RB Xiong , , , J Wang , , , N Zhang , , , 等 . . Deep hybrid collaborative filtering for Web service recommendation . . Expert Syst Appl , , 2018 . . 110 191 - - 205 . . DOI: 10.1016/j.eswa.2018.05.039 http://doi.org/10.1016/j.eswa.2018.05.039 . .

CH Yeung . . Do recommender systems benefit users . . A modeling approach. J Stat Mech Theory Exp , , 2016 . . 4 2 - - 13 . . DOI: 10.1088/1742-5468/2016/04/043401 http://doi.org/10.1088/1742-5468/2016/04/043401 . .

Y Zheng , , , BS Tang , , , WK Ding , , , 等 . . A neural autoregressive approach to collaborative filtering , , 2016 . . https://arxiv.org/abs/1605.09477 https://arxiv.org/abs/1605.09477 , , . .

F Zhou , , , HM Zhou , , , ZH Yang , , , 等 . . EMD2FNN: a strategy combining empirical mode decomposition and factorization machine based neural network for stock market trend prediction . . Expert Syst Appl , , 2018 . . 115 136 - - 151 . . DOI: 10.1016/j.eswa.2018.07.065 http://doi.org/10.1016/j.eswa.2018.07.065 . .

浏览量

129

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Accurate estimation of 6-DoF tooth pose in 3D intraoral scans for dental applications using deep learning

MltAuxTSPP: a unified benchmark for deep learning-based traffic state prediction with multi-source auxiliary data

Q-space-coordinate-guided neural networks for high-fidelity diffusion tensor estimation from minimal diffusion-weighted images

CRGT-SA: an interlaced and spatiotemporal deep learning model for network intrusion detection

Federated model with contrastive learning and adaptive control variates for human activity recognition