Collaborative Recommendation based on Variational Automatic Coding Machine

DOI

10.2991/iccia-19.2019.24How to use a DOI?

Keywords

VAE; Collaborative filtering; Matrix decomposition; Movie recommendation.

Abstract

For the traditional collaborative filtering algorithm, only the scoring information cannot reflect the user's preference, which leads to low recommendation accuracy and easy over-fitting. This paper proposes an improved basic VAE model for film and television programs, adding auxiliary information as a priori of hidden variables. Distribution, will be the first method to use the heterogeneous auxiliary information in the VAE for a priori recommendation; at the same time, integrate multimedia information, add features such as pictures and texts, enrich the hidden variable space, and improve the recommendation effect; finally, open the data set. Experimental tests were performed on MovieLens. Compared with the PMF benchmark model, the algorithm is significantly better than the above method in the root mean square error index.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhiheng Zhang
PY  - 2019/07
DA  - 2019/07
TI  - Collaborative Recommendation based on Variational Automatic Coding Machine
BT  - Proceedings of the 3rd International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2019)
PB  - Atlantis Press
SP  - 158
EP  - 162
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccia-19.2019.24
DO  - 10.2991/iccia-19.2019.24
ID  - Zhang2019/07
ER  -