Non-official Implementation for "Deep Matrix Factorization Models for Recommender Systems"
In Proceedings of the 26th International Joint Conference on Artificial Intelligence. 3119–3125 (IJCAI 2017)
https://www.ijcai.org/Proceedings/2017/0447.pdf
It is not sure that this implementation has same performance with authors' experiments.
(Followed the authors' experimental setups as much as possible.)
* python==3.7.6
* pytorch==1.4.0
* numpy==1.18.1
* pandas==1.0.0
* scipy==1.4.1
If you have any idea to make faster in sparse matrix indexing(input interaction history), please let me know.
cheon.research (at) gmail.com
(some figures will be updated...)