Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/88761
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Two-phase layered learning recommendation via category structure
Author: Ji, K.
Shen, H.
Tian, H.
Wu, Y.
Wu, J.
Citation: Lecture Notes in Artificial Intelligence, 2014 / Tseng, V., Ho, T., Zhou, Z.-H., Chen, A., Kao, H.-Y. (ed./s), vol.8444 LNAI, iss.PART 2, pp.13-24
Publisher: Springer Verlag
Issue Date: 2014
Series/Report no.: Lecture Notes in Computer Science; 8444
ISBN: 9783319066042
ISSN: 0302-9743
1611-3349
Conference Name: 18th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2014) (13 May 2014 - 16 May 2014 : Tainan, Taiwan)
Editor: Tseng, V.
Ho, T.
Zhou, Z.-H.
Chen, A.
Kao, H.-Y.
Statement of
Responsibility: 
Ke Ji, Hong Shen, Hui Tian, Yanbo Wu, Jun Wu
Abstract: Context and social network information have been introduced to improve recommendation systems. However, most existing work still models users’ rating for every item directly. This approach has two disadvantages: high cost for handling large amount of items and unable to handle the dynamic update of items. Generally, items are classified into many categories. Items in the same category have similar/relevant content, and hence may attract users of the same interest. These characteristics determine that we can utilize the item’s content similarity to overcome the difficultiess of large amount and dynamic update of items. In this paper, aiming at fusing the category structure, we propose a novel two-phase layered learning recommendation framework, which is matrix factorization approach and can be seen as a greedy layer-wise training: first learn user’s average rating to every category, and then, based on this, learn more accurate estimates of user’s rating for individual item with content and social relation ensembled. Based on two kinds of classifications, we design two layered gradient algorithms in our framework. Systematic experiments on real data demonstrate that our algorithms outperform other state-of-the-art methods, especially for recommending new items.
Keywords: Collaborative filtering
Matrix Factorization
Recommender Systems
Layered Learning
Rights: © Springer International Publishing Switzerland 2014
DOI: 10.1007/978-3-319-06605-9_2
Appears in Collections:Aurora harvest 2
Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_88761.pdf
  Restricted Access
Restricted Access582.25 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.