Transfer Learning for Global Feature Importance Measurements

Published: 19 Mar 2024, Last Modified: 11 Apr 2024Tiny Papers @ ICLR 2024 NotableEveryoneRevisionsBibTeXCC BY 4.0
Keywords: transfer learning, feature importance, privacy-preserving, electronic health records
Abstract: Understanding feature importance is crucial for conducting interpretable clinical decision-making. However, the reliability of such analyses can be heavily impacted by the available sample size, placing sites with lower data quality and smaller sample sizes at inherent disadvantages. To address the challenge, we propose a model-agnostic transfer learning-based approach for feature importance measurement and evaluate its effectiveness using real-world heterogeneous electronic health records.
Submission Number: 47