Extracting Information Cores with Multi-property Using a Multiobjective Evolutionary Algorithm
Zhenni Ren, Jing Liu · 2019
Recommender systems are efficient tools to alleviate the information overload problem. The information core extraction problem aims at finding a group of users who carry reliable, objective information to represent the system to provide recommendations. Many greedy algorithms have been proposed to deal with this problem, but most algorithms only focus on finding an information core to achieve accurate recommendation results, losing sight of other recommendation objectives with equivalent importance. To this end, we model the information core extraction problem as a multiobjective optimization problem, and propose a multiobjective evolutionary algorithm to extract information cores, labeled as MOEA-IC. MOEA-IC extracts information cores with multi-property at the same time, which can provide candidate solutions with different properties for decision makers. In the experiments, the performance of MOEA-IC is validated on three datasets with varying selection rates and compared with that of two existing greedy algorithms. The experimental results demonstrate the efficiency of MOEA-IC and show that the information core extracted by MOEA-IC can not only be helpful in providing accuracy recommendation, but also provide recommendations of good performance in terms of coverage and diversity criteria. The significance of this study is that the information-core-based recommendation is timesaving, and decision makers can choose information cores with different properties provided by MOEA-IC based on practical requirements.