Integrating metadata into deep autoencoder for handling prediction task of collaborative recommender system

被引:2
作者
Behara, Gopal [1 ]
Yannam, V. Ramanjaneyulu [2 ]
Nayyar, Anand [3 ]
Bagal, Dilip Kumar [4 ]
机构
[1] Govt Coll Engn Kalahandi, Dept Comp Sci & Engn, Bhawanipatna 766003, Orissa, India
[2] Natl Inst Technol, Dept Comp Sci & Engn, Rourkela 569008, Orissa, India
[3] Duy Tan Univ, Fac Informat Technol, Grad Sch, Da Nang 550000, Vietnam
[4] Govt Coll Engn Kalahandi, Dept Mech Engn, Bhawanipatna 766003, Orissa, India
关键词
Collaborative Filtering; Recommender System; Deep Learning; Metadata; Autoencoder; MATRIX FACTORIZATION; IMAGE;
D O I
10.1007/s11042-023-17029-7
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Nowadays, Deep learning (DL) techniques have been proven successful as learning techniques in various research fields ranging from computer vision to social networks. The approach of DL is flourishing in the field of recommender systems (RS). Researchers have deployed metadata or auxiliary information using DL approaches in diverse applications in the last decade to achieve better recommendation accuracy. Thus, the metadata plays a vital role in obtaining a better user-item interaction. At the same time, existing techniques are based on fixed user and item factors. Therefore, the model does not correctly identify actual latent factors representation, resulting in a high prediction error. To handle this problem, a user metadata embedding using a deep autoencoder RS model called "Metadata Embedding Deep AutoEncoder (MEDAE)" based collaborative filtering is proposed. MEDAE model takes embeds user metadata such as demographics along with the rating data. The MEDAE model consists of an embedding layer, Encoder, and Decoder. The embedding layer generates embedding or latent features of the users, items, and metadata; Encoder receives concatenated features of the user, item, and metadata, then encodes the inputs and passes them to the decoder; and the decoder reconstructs the output. To test the effectiveness of proposed model Root Mean Squared Error and Mean Absolute Error measures are used. Different architectures (like Big-Small-Big (BSB) (5), BSB (3), Small-Big-Small (3), and SBS (5)) of the MEDAE model are evaluated on MovieLens datasets along with different parameters such as activation functions (ELU and SELU) and regularization and results concluded that the MEDAE with SBS (3) and ELU + SELU component improves 4% of RMSE and 2% MAE over the baseline methods.
引用
收藏
页码:42125 / 42147
页数:23
相关论文
共 70 条
  • [21] Neural Collaborative Filtering
    He, Xiangnan
    Liao, Lizi
    Zhang, Hanwang
    Nie, Liqiang
    Hu, Xia
    Chua, Tat-Seng
    [J]. PROCEEDINGS OF THE 26TH INTERNATIONAL CONFERENCE ON WORLD WIDE WEB (WWW'17), 2017, : 173 - 182
  • [22] Reducing the dimensionality of data with neural networks
    Hinton, G. E.
    Salakhutdinov, R. R.
    [J]. SCIENCE, 2006, 313 (5786) : 504 - 507
  • [23] Hinton G. E., 1993, P ADV NEUR INF PROC, P3
  • [24] Collaborative filtering in dynamic networks based on deep auto-encoder
    Jalali, Shiva
    Hosseini, Monireh
    [J]. JOURNAL OF SUPERCOMPUTING, 2022, 78 (05) : 7410 - 7427
  • [25] Neural model based collaborative filtering for movie recommendation system
    Jena K.K.
    Bhoi S.K.
    Mallick C.
    Jena S.R.
    Kumar R.
    Long H.V.
    Son N.T.K.
    [J]. International Journal of Information Technology, 2022, 14 (4) : 2067 - 2077
  • [26] Kamalalochana S., 2019, INT J ENG ADV TECHNO, V8, P244, DOI DOI 10.35940/IJEAT.E1049.0585S19
  • [27] Convolutional Matrix Factorization for Document Context-Aware Recommendation
    Kim, Donghyun
    Park, Chanyoung
    Oh, Jinoh
    Lee, Sungyoung
    Yu, Hwanjo
    [J]. PROCEEDINGS OF THE 10TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'16), 2016, : 233 - 240
  • [28] Klambauer G., 2017, Advances in neural information processing systems, P971
  • [29] Koren Y, 2008, P 14 ACM SIGKDD INT, P426, DOI [10.1145/1401890.1401944?, DOI 10.1145/1401890.1401944]
  • [30] MATRIX FACTORIZATION TECHNIQUES FOR RECOMMENDER SYSTEMS
    Koren, Yehuda
    Bell, Robert
    Volinsky, Chris
    [J]. COMPUTER, 2009, 42 (08) : 30 - 37