A Task-Level Explanation Framework for Meta-Learning Algorithms
This work introduces TLXML (Task-Level eXplanation of Meta-Learning), a novel framework that extends influence functions to meta-learning settings, enabling task-level explanations of adaptation and inference, and proposes a Gauss-Newton-based approximation.
Yoshihiro Mitsuka, Shadan Golestan, Zahin Sufiyan et al.
· 0 citations