CLC number: TP391
On-line Access: 2024-08-27
Received: 2023-10-17
Revision Accepted: 2024-05-08
Crosschecked: 2020-06-22
Cited: 0
Clicked: 6924
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.
@article{title="DAN: a deep association neural network approach for personalization recommendation",
author="Xu-na Wang, Qing-mei Tan",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="21",
number="7",
pages="963-980",
year="2020",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1900236"
}
%0 Journal Article
%T DAN: a deep association neural network approach for personalization recommendation
%A Xu-na Wang
%A Qing-mei Tan
%J Frontiers of Information Technology & Electronic Engineering
%V 21
%N 7
%P 963-980
%@ 2095-9184
%D 2020
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1900236
TY - JOUR
T1 - DAN: a deep association neural network approach for personalization recommendation
A1 - Xu-na Wang
A1 - Qing-mei Tan
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 21
IS - 7
SP - 963
EP - 980
%@ 2095-9184
Y1 - 2020
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1900236
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.
[1]Aiolli F, 2014. Convex AUC optimization for top-n recommendation with implicit feedback. Proc 8th ACM Conf on Recommender Systems, p.293-296.
[2]Barkan O, Koenigstein N, 2016. Item2Vec: neural item embedding for collaborative filtering. Proc IEEE 26th Int Workshop on Machine Learning for Signal Processing, p.1-6.
[3]Bayer I, He XN, Kanagal B, et al., 2017. A generic coordinate descent framework for learning from implicit feedback. Proc 26th Int Conf on World Wide Web, p.1341-1350.
[4]Buettner R, 2016. Predicting user behavior in electronic markets based on personality-mining in large online social networks. Electron Mark, 27(3):247-265.
[5]Cao YL, Li WL, Zheng DX, 2018. An improved neighborhood- aware unified probabilistic matrix factorization recommendation. Wirel Pers Commun, 102(4):3121-3140.
[6]Cheng G, Yang CY, Yao XW, et al., 2018. When deep learning meets metric learning: remote sensing image scene classification via learning discriminative CNNs. IEEE Trans Geosci Remote Sens, 56(5):2811-2821.
[7]del Corso GM, Gianna M, Romani F, 2019. Adaptive nonnegative matrix factorization and measure comparisons for recommender systems. Appl Math Comput, 354:164-179.
[8]Elkahky AM, Song Y, He XD, 2015. A multi-view deep learning approach for cross domain user modeling in recommendation systems. Proc 24th Int Conf on World Wide Web, p.278-288.
[9]Fu MS, Qu H, Yi Z, et al., 2019. A novel deep learning-based collaborative filtering model for recommendation system. IEEE Trans Cybern, 49(3):1084-1096.
[10]Guo HF, Tang RM, Ye YM, et al., 2017. DeepFM: a factorization- machine based neural network for CTR prediction. https://arxiv.org/abs/1703.04247
[11]Ha T, Lee S, 2017. Item-network-based collaborative filtering: a personalized recommendation method based on a user’s item network. Inform Process Manag, 53(5):1171-1184.
[12]He XN, Zhang HW, Kan MY, et al., 2016. Fast matrix factorization for online recommendation with implicit feedback. Proc 39th Int ACM SIGIR Conf on Research and Development in Information Retrieval, p.549-558.
[13]He XN, Liao LZ, Zhang HW, et al., 2017. Neural collaborative filtering. Proc 26th Int Conf on World Wide Web, p.173- 182.
[14]He XN, Du XY, Wang X, et al., 2018. Outer product-based neural collaborative filtering. https://arxiv.org/abs/1808.03912
[15]Hernando A, Bobadilla J, Ortega F, 2016. A non negative matrix factorization for collaborative filtering recommender systems based on a Bayesian probabilistic model. Knowl-Based Syst, 97:188-202.
[16]Hossain MS, Muhammad G, 2018. Emotion recognition using deep learning approach from audio-visual emotional big data. Inform Fus, 49:69-78.
[17]Hsu CC, Yeh MY, Lin SD, 2018. A general framework for implicit and explicit social recommendation. IEEE Trans Knowl Data Eng, 30(12):2228-2241.
[18]Jia XW, Li XY, Kang L, et al., 2016. Collaborative restricted Boltzmann machine for social event recommendation. IEEE/ACM Int Conf on Advances in Social Networks Analysis and Mining, p.402-405.
[19]Jung JJ, 2012. Attribute selection-based recommendation framework for short-head user group: an empirical study by MovieLens and IMDB. Expert Syst Appl, 39(4):4049- 4054.
[20]Knoll J, Stübinger J, Grottke M, 2019. Exploiting social media with higher-order factorization machines: statistical arbitrage on high-frequency data of the S&P 500. Quant Finan, 19(4):571-585.
[21]Li Y, Wang SH, Pan Q, et al., 2019. Learning binary codes with neural collaborative filtering for efficient recommendation systems. Knowl-Based Syst, 172:64-75.
[22]Li ZC, Tang JH, 2017. Weakly supervised deep matrix factorization for social image understanding. IEEE Trans Image Process, 26(1):276-288.
[23]Liu JT, Wu CH, 2017. Deep learning based recommendation: a survey. Int Conf on Information Science and Applications, p.451-458.
[24]Liu WB, Wang ZD, Liu XH, et al., 2017. A survey of deep neural network architectures and their applications. Neurocomputing, 234:11-26.
[25]Liu Y, Li LF, Liu J, 2018. Bilateral neural embedding for collaborative filtering-based multimedia recommendation. Multim Tools Appl, 77(10):12533-12544.
[26]Lu J, Wu DS, Mao MS, et al., 2015. Recommender system application developments: a survey. Dec Supp Syst, 74:12-32.
[27]Luo L, Xie HR, Rao YH, et al., 2018. Personalized recommendation by matrix co-factorization with tags and time information. Expert Syst Appl, 119:311-321.
[28]Ma C, Zhang YX, Wang QL, et al., 2018. Point-of-interest recommendation: exploiting self-attentive autoencoders with neighbor-aware influence. Proc 27th ACM Int Conf on Information and Knowledge Management, p.697-706.
[29]Marchi E, Vesperini F, Eyben F, et al., 2015. 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, p.1996-2000.
[30]Noda K, Yamaguchi Y, Nakadai K, et al., 2015. Audio-visual speech recognition using deep learning. Appl Intell, 42:722-737.
[31]Pan J, Zi YY, Chen JL, et al., 2017. LiftingNet: a novel deep learning network with layerwise feature learning from noisy mechanical data for fault classification. IEEE Trans Ind Electron, 65(6):4973-4982.
[32]Pan WK, Chen L, Ming Z, 2019. Personalized recommendation with implicit feedback via learning pairwise preferences over item-sets. Knowl Inform Syst, 58(2):295-318.
[33]Verstrepen K, Bhaduriy K, Cule B, et al., 2017. Collaborative filtering for binary, positiveonly data. ACM SIGKDD Explor Newsl, 19(1):1-21.
[34]Wang XN, Tan QM, Zhang LF, 2020. A deep neural network of multi-form alliances for personalized recommendations. Inform Sci, 531:68-86.
[35]Wu L, Chen EH, Liu Q, et al., 2012. Leveraging tagging for neighborhood-aware probabilistic matrix factorization. Proc 21st ACM Int Conf on Information and Knowledge Management, p.1854-1858.
[36]Xiao YY, Wang GW, Hsu CH, et al., 2018. A time-sensitive personalized recommendation method based on probabilistic matrix factorization technique. Soft Comput, 22(20):6785-6796.
[37]Xiong RB, Wang J, Zhang N, et al., 2018. Deep hybrid collaborative filtering for Web service recommendation. Expert Syst Appl, 110:191-205.
[38]Yeung CH, 2016. Do recommender systems benefit users? A modeling approach. J Stat Mech Theory Exp, 4:2-13.
[39]Zheng Y, Tang BS, Ding WK, et al., 2016. A neural autoregressive approach to collaborative filtering. https://arxiv.org/abs/1605.09477
[40]Zhou F, Zhou HM, Yang ZH, et al., 2018. EMD2FNN: a strategy combining empirical mode decomposition and factorization machine based neural network for stock market trend prediction. Expert Syst Appl, 115:136-151.
Open peer comments: Debate/Discuss/Question/Opinion
<1>