Convolutional Gaussian Embeddings for Personalized Recommendation with Uncertainty

Convolutional Gaussian Embeddings for Personalized Recommendation with Uncertainty

Junyang Jiang, Deqing Yang, Yanghua Xiao, Chenlu Shen

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Main track. Pages 2642-2648. https://doi.org/10.24963/ijcai.2019/367

Most of existing embedding based recommendation models use embeddings (vectors) to represent users and items which contain latent features of users and items. Each of such embeddings corresponds to a single fixed point in low-dimensional space, thus fails to precisely represent the users/items with uncertainty which are often observed in recommender systems. Addressing this problem, we propose a unified deep recommendation framework employing Gaussian embeddings, which are proven adaptive to uncertain preferences exhibited by some users, resulting in better user representations and recommendation performance. Furthermore, our framework adopts Monte-Carlo sampling and convolutional neural networks to compute the correlation between the objective user and the candidate item, based on which precise recommendations are achieved. Our extensive experiments on two benchmark datasets not only justify that our proposed Gaussian embeddings capture the uncertainty of users very well, but also demonstrate its superior performance over the state-of-the-art recommendation models.
Keywords:
Machine Learning: Data Mining
Uncertainty in AI: Uncertainty Representations
Machine Learning: Deep Learning
Machine Learning: Recommender Systems
Multidisciplinary Topics and Applications: Recommender Systems