The cold-start recommendation is an urgent problem in contemporary online applications . Many data-driven algorithms, suchas the widely used matrix factorization, underperform because of datasparseness . This work adopts the idea of meta-learning to solve the user’scold start recommendation problem . The proposed metaCSR holds the ability to learn the common patterns from regular users’ behaviors and optimize the initialization so that the model can quickly adapt to new users after one or a few gradient updates to achieve optimal performance . The extensive quantitative experiments on three widely-used datasets show the remarkable performance of meta CSR indealing with user cold start problem . Meanwhile, a series of qualitativeanalysis demonstrates that the proposed MetaCSR has good generalization. Meanwhile, the proposed metaCRSR has a goodGeneralization. The proposed proposals have good

Author(s) : Xiaowen Huang, Jitao Sang, Jian Yu, Changsheng Xu

Links : PDF - Abstract

Code :
Coursera

Keywords : start - proposed - problem - cold - meta -

Leave a Reply

Your email address will not be published. Required fields are marked *