A correlative denoising autoencoder to model social influence for top- N recommender system

In recent years, there are numerous works been proposed to leverage the techniques of deep learning to improve social-aware recommendation performance. In most cases, it requires a larger number of data to train a robust deep learning model, which contains a lot of parameters to fit training data. H...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Frontiers of Computer Science Ročník 14; číslo 3; s. 143301
Hlavní autoři: PAN, Yiteng, HE, Fazhi, YU, Haiping
Médium: Journal Article
Jazyk:angličtina
Vydáno: Beijing Higher Education Press 01.06.2020
Springer Nature B.V
Témata:
Algorithms
Artificial neural networks
Computer Science
Correlation
Deep learning
denoising autoencoder
Machine learning
Mathematical models
neural network
Noise reduction
Parameters
recommender system
Recommender systems
Regularization
Research Article
Robustness
social network
Social networks
social network
recommender system
denoising autoencoder
neural network
ISSN:2095-2228, 2095-2236
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In recent years, there are numerous works been proposed to leverage the techniques of deep learning to improve social-aware recommendation performance. In most cases, it requires a larger number of data to train a robust deep learning model, which contains a lot of parameters to fit training data. However, both data of user ratings and social networks are facing critical sparse problem, which makes it not easy to train a robust deep neural networkmodel. Towards this problem, we propose a novel correlative denoising autoencoder (CoDAE) method by taking correlations between users with multiple roles into account to learn robust representations from sparse inputs of ratings and social networks for recommendation. We develop the CoDAE model by utilizing three separated autoencoders to learn user featureswith roles of rater, truster and trustee, respectively. Especially, on account of that each input unit of user vectors with roles of truster and trustee is corresponding to a particular user, we propose to utilize shared parameters to learn common information of the units that corresponding to same users. Moreover, we propose a related regularization term to learn correlations between user features that learnt by the three subnetworks of CoDAE model. We further conduct a series of experiments to evaluate the proposed method on two public datasets for Top-N recommendation task. The experimental results demonstrate that the proposed model outperforms state-of-the-art algorithms on rank-sensitive metrics of MAP and NDCG.
Bibliografie:social network
recommender system
denoising autoencoder
Document received on :2018-03-31
Document accepted on :2019-03-01
neural network
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2095-2228
2095-2236
DOI:10.1007/s11704-019-8123-3