Embedding-Augmented Generalized Matrix Factorization for Recommendation With Implicit Feedback

Learning effective representations of users and items is crucially important to recommendation with implicit feedback. Matrix factorization is the basic idea to derive the representations of users and items by decomposing the given interaction matrix. However, existing matrix factorization based approaches share the limitation in that the interaction between user embedding and item embedding is only weakly enforced by fitting the given individual rating value, which may lose potentially useful information. In this article, we propose a novel augmented generalized matrix factorization approach that is able to incorporate the historical interaction information of users and items for learning effective representations of users and items. Despite the simplicity of our proposed approach, extensive experiments on four public implicit feedback datasets demonstrate that our approach outperforms state-of-the-art counterparts. Furthermore, the ablation study demonstrates that by using the historical interactions to enrich user embedding and item embedding for generalized matrix factorization, better performance, faster convergence, and lower training loss can be achieved.

Authors

• Lei Feng Singapore University of Technology and Design
• Hongxin Wei Nanyang Technological University
• Qingyu Guo
• Zhuoyi Lin Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR)
• Bo An Nanyang Technological University Skywork AI

Keywords

• Encoding
• Intelligent systems
• Matrix decomposition
• Convergence
• Training data
• Recommender systems
• Collaboration
• Matrix Factorization
• Implicit Feedback
• Generalized Matrix Factorization
• Neural Network
• Deep Neural Network
• Interaction Score
• Attention Model
• Latent Features
• Latent Vector
• History Of Interactions
• One-hot Encoding
• Collaborative Filtering
• High-level Description
• User Representation
• Latent Factor Model
• Activation Function
• Attention Mechanism
• Weight Vector
• Pooling Layer
• Matrix Factorization Model
• Augmented Vector
• Target Items
• Target User
• Regularization Parameter
• Attention Weights
• Element-wise Product
• Interactive Way
• Training Epochs
• multi-hot encoding
• representation learning