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

פרסום מחקרי: פרסום בכתב עתמאמר מכנסביקורת עמיתים

תקציר

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.

שפה מקוריתאנגלית
עמודים (מ-עד)1510-1521
מספר עמודים12
כתב עתProceedings of Machine Learning Research
כרך216
סטטוס פרסוםפורסם - 2023
אירוע39th Conference on Uncertainty in Artificial Intelligence, UAI 2023 - Pittsburgh, ארצות הברית
משך הזמן: 31 יולי 20234 אוג׳ 2023

הערה ביבליוגרפית

Publisher Copyright:
© UAI 2023. All rights reserved.

טביעת אצבע

להלן מוצגים תחומי המחקר של הפרסום 'Simple Transferability Estimation for Regression Tasks'. יחד הם יוצרים טביעת אצבע ייחודית.

פורמט ציטוט ביבליוגרפי