Recommendation system using a deep learning and graph analysis approach
This addresses challenges in recommendation systems for users facing information overload, though it appears incremental as it builds on existing techniques like Matrix Factorization and deep learning.
The paper tackles cold-start and sparsity problems in recommender systems by proposing a method that combines Matrix Factorization, graph analysis, and deep Autoencoders, achieving superior performance over state-of-the-art methods on two standard datasets.
When a user connects to the Internet to fulfill his needs, he often encounters a huge amount of related information. Recommender systems are the techniques for massively filtering information and offering the items that users find them satisfying and interesting. The advances in machine learning methods, especially deep learning, have led to great achievements in recommender systems, although these systems still suffer from challenges such as cold-start and sparsity problems. To solve these problems, context information such as user communication network is usually used. In this paper, we have proposed a novel recommendation method based on Matrix Factorization and graph analysis methods. In addition, we leverage deep Autoencoders to initialize users and items latent factors, and deep embedding method gathers users' latent factors from the user trust graph. The proposed method is implemented on two standard datasets. The experimental results and comparisons demonstrate that the proposed approach is superior to the existing state-of-the-art recommendation methods. Our approach outperforms other comparative methods and achieves great improvements.