Initialization matters : regularizing manifold-informed initialization for neural recommendation systems

• Main Authors: Zhang, Yinan, Li, Boyang, Liu, Yong, Wang, Hao, Miao, Chunyan
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2021
• Subjects: Engineering::Computer science and engineering; Network Initialization; Recommender Systems
• Online Access: https://hdl.handle.net/10356/153528
• Institution: Nanyang Technological University

Proper initialization is crucial to the optimization and the generalization of neural networks. However, most existing neural recommendation systems initialize the user and item embeddings randomly. In this work, we propose a new initialization scheme for user and item embeddings called Laplacian E...