Abstract
Representation learning has attracted growing attention in recommendation system. In addition, deep learning has been adopted to build a representation generator based on content data (e.g., reviews, descriptions), and has been verified to be an excellent method for recommendation system. However, the content data may not be sufficient to capture the hidden features of user behavior patterns. We argue that the underlying information in behavior patterns can characterize users, by generating specific representation from user activities. In this paper, we propose a deep transfer learning-based recommendation model (DeepTransferR), which conducts knowledge transfer from multiple user activities. We adopt attention network to migrate the behavior pattern from auxiliary activities, and to generate personalized representations for users. In DeepTransferR, we set up an independent predictor for each user activity. We then define a weighted loss function to model knowledge interaction by incorporating the independent loss in each activity predictor. Experiments have been conducted on real-world datasets, and the results show that the proposed model outperforms the state-of-the-art methods in not only recommendation performance, but also convergence and robustness in sparse-data and cold-start environments.
Similar content being viewed by others
Data availability
Enquiries about data availability should be directed to the authors.
References
Bansal T, Belanger D, McCallum A (2016) Ask the GRU: multi-task learning for deep text recommendations. In: RecSys 2016—Proceedings of the 10th ACM conference on recommender systems. pp 107–114. https://doi.org/10.1145/2959100.2959180
Cami BR, Hassanpour H, Mashayekhi H (2019) User preferences modeling using dirichlet process mixture model for a content-based recommender system. Knowl Based Syst. https://doi.org/10.1016/j.knosys.2018.09.028
Chae DK, Kim SW, Lee JT (2019) Autoencoder-based personalized ranking framework unifying explicit and implicit feedback for accurate top-N recommendation. Knowl Based Syst. https://doi.org/10.1016/j.knosys.2019.03.026
Chen X, Lei C, Liu D et al (2021) E-Commerce storytelling recommendation using attentional domain-transfer network and adversarial pre-training. IEEE Trans Multimed. https://doi.org/10.1109/tmm.2021.3054525
Cheng HT, Koc L, Harmsen J, et al (2016) Wide and deep learning for recommender systems. In: ACM International conference proceeding series
Cinar YG, Mirisaee H, Goswami P et al (2018) Period-aware content attention RNNs for time series forecasting with missing values. Neurocomputing. https://doi.org/10.1016/j.neucom.2018.05.090
Cui Q, Wu S, Huang Y, Wang L (2019) A hierarchical contextual attention-based network for sequential recommendation. Neurocomputing. https://doi.org/10.1016/j.neucom.2019.04.073
Da’u A, Salim N, Rabiu I, Osman A (2020) Recommendation system exploiting aspect-based opinion mining with deep learning method. Inf Sci (Ny) https://doi.org/10.1016/j.ins.2019.10.038
Dave VS, Al Hasan M, Zhang B, et al (2018) A combined representation learning approach for better job and skill recommendation. In: International conference on information and knowledge management, proceedings
Desai NA, Ganatra A (2015) Buying scenario and recommendation of purchase by constraint based sequential pattern mining from time stamp based sequential dataset. Proc Comput Sci 45:166–175
Gan M, Xiao K (2019) R-RNN: extracting user recent behavior sequence for click-through rate prediction. IEEE Access 7:111767–111777. https://doi.org/10.1109/ACCESS.2019.2927717
Gasparic M, Murphy GC, Ricci F (2017) A context model for IDE-based recommendation systems. J Syst Softw. https://doi.org/10.1016/j.jss.2016.09.012
Guan J, Xu M, Kong X (2018) Learning social regularized user representation in recommender system. Signal Process. https://doi.org/10.1016/j.sigpro.2017.09.015
Huang F, Zhang X, Zhao Z et al (2018) Deep multi-view representation learning for social images. Appl Soft Comput J. https://doi.org/10.1016/j.asoc.2018.08.010
Jain A, Singh PK, Dhar J (2020) Multi-objective item evaluation for diverse as well as novel item recommendations. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2019.112857
Jiang R, Song X, Fan Z et al (2021) Transfer urban human mobility via POI embedding over multiple cities. ACM/IMS Trans Data Sci. https://doi.org/10.1145/3416914
Khan ZY, Niu Z, Yousif A (2020) Joint deep recommendation model exploiting reviews and metadata information. Neurocomputing. https://doi.org/10.1016/j.neucom.2020.03.075
Kim D, Park C, Oh J, et al (2016) Convolutional matrix factorization for document context-aware recommendation. In: RecSys 2016: Proceedings of the 10th ACM conference on recommender systems
Liu H, Wang Y, Peng Q et al (2020a) Hybrid neural recommendation with joint deep representation learning of ratings and reviews. Neurocomputing. https://doi.org/10.1016/j.neucom.2019.09.052
Liu H, Wu Z, Zhang X (2018) CPLR: Collaborative pairwise learning to rank for personalized recommendation. Knowl Based Syst. https://doi.org/10.1016/j.knosys.2018.02.023
Liu Y, Tian Z, Sun J et al (2020b) Distributed representation learning via node2vec for implicit feedback recommendation. Neural Comput Appl. https://doi.org/10.1007/s00521-018-03964-2
Liu Z, Guo S, Wang L et al (2019) A multi-objective service composition recommendation method for individualized customer: hybrid MPA-GSO-DNN model. Comput Ind Eng. https://doi.org/10.1016/j.cie.2018.12.042
Lu H, Chen C, Kong M et al (2016) Social recommendation via multi-view user preference learning. Neurocomputing. https://doi.org/10.1016/j.neucom.2016.07.011
Luo L, Xie H, Rao Y, Wang FL (2019) Personalized recommendation by matrix co-factorization with tags and time information. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2018.11.003
Luo S, Lu X, Wu J, Yuan J (2021) Review-aware neural recommendation with cross-modality mutual attention. Int Conf Inf Knowl Manag Proc. https://doi.org/10.1145/3459637.3482172
Ma J, Zhao Z, Yi X et al (2018a) Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. Proc ACM SIGKDD Int Conf Knowl Discov Data Min. https://doi.org/10.1145/3219819.3220007
Ma X, Zhao L, Huang G, et al (2018b) Entire space multi-task model: an effective approach for estimating post-click conversion rate. In: 41st International ACM SIGIR conference on research and development in information retrieval, SIGIR 2018b
Ma Y, Gan M (2021) DeepAssociate: a deep learning model exploring sequential influence and history-candidate association for sequence recommendation. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2021.115587
Mongia A, Jhamb N, Chouzenoux E, Majumdar A (2020) Deep latent factor model for collaborative filtering. Signal Process. https://doi.org/10.1016/j.sigpro.2019.107366
Nassar N, Jafar A, Rahhal Y (2020) A novel deep multi-criteria collaborative filtering model for recommendation system. Knowl Based Syst. https://doi.org/10.1016/j.knosys.2019.06.019
Ni Y, Ou D, Liu S, et al (2018) Perceive your users in depth
Niu J, Wang L, Liu X, Yu S (2016) FUIR: Fusing user and item information to deal with data sparsity by using side information in recommendation systems. J Netw Comput Appl. https://doi.org/10.1016/j.jnca.2016.05.006
Pan W (2016) A survey of transfer learning for collaborative recommendation with auxiliary data. Neurocomputing. https://doi.org/10.1016/j.neucom.2015.11.059
Qiao Y, Luo X, Li C et al (2020) Heterogeneous graph-based joint representation learning for users and POIs in location-based social network. Inf Process Manag. https://doi.org/10.1016/j.ipm.2019.102151
Schreiner T, Rese A, Baier D (2019) Multichannel personalization: Identifying consumer preferences for product recommendations in advertisements across different media channels. J Retail Consum Serv. https://doi.org/10.1016/j.jretconser.2019.02.010
Tao Z, Wang X, He X et al (2019) HoAFM: a high-order attentive factorization machine for CTR prediction. Inf Process Manag. https://doi.org/10.1016/j.ipm.2019.102076
Unger M, Bar A, Shapira B, Rokach L (2016) Towards latent context-aware recommendation systems. Knowl Based Syst. https://doi.org/10.1016/j.knosys.2016.04.020
Wang Z, Xia H, Du B et al (2020) Joint representation learning with ratings and reviews for recommendation. Neurocomputing. https://doi.org/10.1016/j.neucom.2020.04.033
Wu B, Wen W, Hao Z, Cai R (2020) Multi-context aware user–item embedding for recommendation. Neural Netw. https://doi.org/10.1016/j.neunet.2020.01.008
Wu L, Quan C, Li C et al (2019) A context-aware user-item representation learning for item recommendation. ACM Trans Inf Syst 37:1–29
Xu C (2019) A big-data oriented recommendation method based on multi-objective optimization. Knowl Based Syst. https://doi.org/10.1016/j.knosys.2019.03.032
Zhang Y, Ai Q, Chen X, Croft WB (2017) Joint representation learning for top-N recommendation with heterogeneous information sources. In: International conference on information and knowledge management, proceedings
Zhao J, Geng X, Zhou J et al (2019) Attribute mapping and autoencoder neural network based matrix factorization initialization for recommendation systems. Knowl Based Syst. https://doi.org/10.1016/j.knosys.2018.12.022
Zhao L, Pan SJ, Yang Q (2017) A unified framework of active transfer learning for cross-system recommendation. Artif Intell. https://doi.org/10.1016/j.artint.2016.12.004
Zheng Y, Zhang R, Wang S, et al (2020) Anchored model transfer and soft instance transfer for cross-task cross-domain learning: a study through aspect-level sentiment classification. In: The web conference 2020: Proceedings of the world wide web conference, WWW 2020
Zhu H, Li X, Zhang P, et al (2018) Learning tree-based deep model for recommender systems. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining
Zhuang F, Luo D, Yuan NJ, et al (2017a) Representation learning with pair-wise constraints for collaborative ranking. In: WSDM 2017a - Proceedings of the 10th ACM international conference on web search and data mining
Zhuang F, Zhang Z, Qian M et al (2017b) Representation learning via Dual-Autoencoder for recommendation. Neural Netw. https://doi.org/10.1016/j.neunet.2017.03.009
Funding
This work was supported by the National Natural Science Foundation of China (Nos. 71871019, 71471016, 71729001).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict interests
The authors have not disclosed any competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gan, M., Ma, Y. Knowledge transfer learning from multiple user activities to improve personalized recommendation. Soft Comput 26, 6547–6566 (2022). https://doi.org/10.1007/s00500-022-07178-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-022-07178-6