The information on the Internet is increasingly complicated, users can not use the search engine to accurately find effective information. But the emergence of the recommendation system can effectively alleviate this problem. Algorithms such as collaborative filtering have a large drop in recommended quality when user ratings are sparse.  We propose a novel cross attentive collaborative filtering model. Our model can learn more about the potential relationships between users, items and ratings. To validate the validity of the algorithm model, experiments were performed on public datasets. The experimental results show that the mae and rmse index have decreased.

Rongjie Shan, Wenming Ma, Mingming Qi. Cross Attentive Collaborative Filtering for Recommender Systems. Academic Journal of Computing & Information Science (2020), Vol. 3, Issue 1: 17-23. https://doi.org/10.25236/AJCIS.2020.030102.

[1] J.Bobadilla.,F.Ortega.,Hernando,et al(2013).Recommender systems survey. Knowledge Based Systems 46,p.109-132.
[2] R.Burke(2012).Hybrid recommender systems:Survey and experiments.In User modeling and user-adapted interaction,p.331-370.
[3] Xiangnan He,LiziLi Zhao，Hanwang Zhang et al(2017).In Neural Collaborative Filtering.International World Wide Web Conference Committee.
[4] D.Lee,HS.Seung(2001).Algorithms for non-negative matrix factorization . In Advances in neural information provessing systems.p.556-560.
[5] P.Peng,L.Xiao,et al(2017).Recommendation algorithm based on uer trust and interest with probability matrix factorization,In International Conference on Advanced Cloud & Big Data.IEEE Computer Society,p.355-361.
[6] X. He,H. Zhang,M.-Y. Kan,and T.-S.Chua(2016).Fast matrix factorization for online recommendation with implicit feedback . In SIGIR.p.549-558.
[7] A.Vaswani,N.Siiazeer,N.Parmar,et al(2017). Attention ia all you need.In Advances in Neural Information Processing Systems,p.5998-6008
[8] N. Srivastava and R.Salakhutdinov(2012).Multimodal learning with deep boltzmann machines. In NIPS,p.2222-2230.