Attention based collaborative filtering
Izvestiya of Saratov University. Mathematics. Mechanics. Informatics, Tome 22 (2022) no. 1, pp. 103-111

Voir la notice de l'article provenant de la source Math-Net.Ru

Attention mechanism invention was an important milestone in the development of the Natural Language Processing domain. It found many applications in different fields, like churn prediction, computer vision, speech recognition, and so on. Many state-of-the-art models are based on attention mechanisms, especially in NLP. As this technique is very powerful, we decided to investigate its application in solving a collaborative filtering problem. In this paper, we propose a standard framework for developing a recommender system engine based on transformer architecture. We could not reproduce current state-of-the-art results on MovieLens datasets, but in our implementation attention based model achieves competitive scores on MovieLens 1M and MovieLens 10M datasets.
@article{ISU_2022_22_1_a6,
     author = {A. I. Romanov and I. A. Batraeva},
     title = {Attention based collaborative filtering},
     journal = {Izvestiya of Saratov University. Mathematics. Mechanics. Informatics},
     pages = {103--111},
     publisher = {mathdoc},
     volume = {22},
     number = {1},
     year = {2022},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/ISU_2022_22_1_a6/}
}
TY  - JOUR
AU  - A. I. Romanov
AU  - I. A. Batraeva
TI  - Attention based collaborative filtering
JO  - Izvestiya of Saratov University. Mathematics. Mechanics. Informatics
PY  - 2022
SP  - 103
EP  - 111
VL  - 22
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ISU_2022_22_1_a6/
LA  - en
ID  - ISU_2022_22_1_a6
ER  - 
%0 Journal Article
%A A. I. Romanov
%A I. A. Batraeva
%T Attention based collaborative filtering
%J Izvestiya of Saratov University. Mathematics. Mechanics. Informatics
%D 2022
%P 103-111
%V 22
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ISU_2022_22_1_a6/
%G en
%F ISU_2022_22_1_a6
A. I. Romanov; I. A. Batraeva. Attention based collaborative filtering. Izvestiya of Saratov University. Mathematics. Mechanics. Informatics, Tome 22 (2022) no. 1, pp. 103-111. http://geodesic.mathdoc.fr/item/ISU_2022_22_1_a6/