A recommendation system for meta-modeling: A meta-learning based approach
作者：
Highlights：
• A meta-learning based recommendation system for meta-modeling is proposed.
• Novel meta-features for geometrical characterization on black-box problems are proposed.
• Model-based meta-learners generally outperforms instance-based meta-leaners.
• Singular value decomposition boosts the performance of the recommendation system.
• Experimental results indicate the proposed system significantly improves the modeling efficiency and facilitates model selection.
摘要
•A meta-learning based recommendation system for meta-modeling is proposed.•Novel meta-features for geometrical characterization on black-box problems are proposed.•Model-based meta-learners generally outperforms instance-based meta-leaners.•Singular value decomposition boosts the performance of the recommendation system.•Experimental results indicate the proposed system significantly improves the modeling efficiency and facilitates model selection.
论文关键词：Meta-learning,Meta-model,Simulation,Recommendation system,Algorithm selection,Feature reduction
论文评审过程：Received 14 January 2015, Revised 18 October 2015, Accepted 19 October 2015, Available online 24 October 2015, Version of Record 18 November 2015.
论文官网地址：https://doi.org/10.1016/j.eswa.2015.10.021
