Development of Integrated Quantum Inspired Algorithms for Shapley Value based Fast and Interpretable Feature Subset Selection

• Project/Area Number: 24K15089
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 61030:Intelligent informatics-related
• Research Institution: Iwate Prefectural University
• Principal Investigator: チャクラボルティ バサビ 岩手県立大学, その他部局等, 特命教授 (90305293)
• Co-Investigator(Kenkyū-buntansha): 白田 由香利 学習院大学, 経済学部, 教授 (30337901)
• Project Period (FY): 2024-04-01 – 2027-03-31
• Project Status: Granted (Fiscal Year 2024)
• Budget Amount: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000); Fiscal Year 2026: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2025: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2024: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
• Keywords: Quantum Machine Learning

Outline of Research at the Start

In the analysis of high dimensional medical, healthcare or finance data, transparency in decision is absolutely important. Selection of the relevant and interpretable features is key to the success of transparent and explainable models. The main objective of this research is to investigate and develop extension of Shapley values (SV) to quantum domain and integrate with our already developed quantum inspired metaheuristic approaches for faster implementation of interpretable optimal feature subset selection algorithms leading to quantum based explainable learning models.