Simple Transferability Estimation for Regression Tasks

Cuong N. Nguyen, Phong Tran, Lam Si Tung Ho, Vu Dinh, Anh T. Tran, Tal Hassner, Cuong V. Nguyen

نتاج البحث: نشر في مجلةمقالة من مؤنمرمراجعة النظراء


We consider transferability estimation, the problem of estimating how well deep learning models transfer from a source to a target task. We focus on regression tasks, which received little previous attention, and propose two simple and computationally efficient approaches that estimate transferability based on the negative regularized mean squared error of a linear regression model. We prove novel theoretical results connecting our approaches to the actual transferability of the optimal target models obtained from the transfer learning process. Despite their simplicity, our approaches significantly outperform existing state-of-the-art regression transferability estimators in both accuracy and efficiency. On two large-scale keypoint regression benchmarks, our approaches yield 12% to 36% better results on average while being at least 27% faster than previous state-of-the-art methods.

اللغة الأصليةالإنجليزيّة
الصفحات (من إلى)1510-1521
عدد الصفحات12
دوريةProceedings of Machine Learning Research
مستوى الصوت216
حالة النشرنُشِر - 2023
الحدث39th Conference on Uncertainty in Artificial Intelligence, UAI 2023 - Pittsburgh, الولايات المتّحدة
المدة: ٣١ يوليو ٢٠٢٣٤ أغسطس ٢٠٢٣

ملاحظة ببليوغرافية

Publisher Copyright:
© UAI 2023. All rights reserved.


أدرس بدقة موضوعات البحث “Simple Transferability Estimation for Regression Tasks'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا