LGMar 10, 2022

PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks

DeepMind
arXiv:2203.05126v240 citationsh-index: 37
Originality Highly original
AI Analysis

This addresses the need for better pretrained model selection in transfer learning, offering a theoretically motivated improvement over heuristic approaches.

The paper tackles the problem of selecting the best pretrained model for downstream classification tasks by introducing PACTran, a theoretically grounded family of metrics derived from PAC-Bayesian bounds, and shows it is more consistent and effective than existing methods in evaluations on vision and language-and-vision tasks.

With the increasing abundance of pretrained models in recent years, the problem of selecting the best pretrained checkpoint for a particular downstream classification task has been gaining increased attention. Although several methods have recently been proposed to tackle the selection problem (e.g. LEEP, H-score), these methods resort to applying heuristics that are not well motivated by learning theory. In this paper we present PACTran, a theoretically grounded family of metrics for pretrained model selection and transferability measurement. We first show how to derive PACTran metrics from the optimal PAC-Bayesian bound under the transfer learning setting. We then empirically evaluate three metric instantiations of PACTran on a number of vision tasks (VTAB) as well as a language-and-vision (OKVQA) task. An analysis of the results shows PACTran is a more consistent and effective transferability measure compared to existing selection methods.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes