The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning

by   Anders Andreassen, et al.

Although machine learning models typically experience a drop in performance on out-of-distribution data, accuracies on in- versus out-of-distribution data are widely observed to follow a single linear trend when evaluated across a testbed of models. Models that are more accurate on the out-of-distribution data relative to this baseline exhibit "effective robustness" and are exceedingly rare. Identifying such models, and understanding their properties, is key to improving out-of-distribution performance. We conduct a thorough empirical investigation of effective robustness during fine-tuning and surprisingly find that models pre-trained on larger datasets exhibit effective robustness during training that vanishes at convergence. We study how properties of the data influence effective robustness, and we show that it increases with the larger size, more diversity, and higher example difficulty of the dataset. We also find that models that display effective robustness are able to correctly classify 10 model gets correct. Finally, we discuss several strategies for scaling effective robustness to the high-accuracy regime to improve the out-of-distribution accuracy of state-of-the-art models.



There are no comments yet.


page 24


Robust fine-tuning of zero-shot models

Large pre-trained models such as CLIP offer consistent accuracy across a...

Improving the Adversarial Robustness of Transfer Learning via Noisy Feature Distillation

Fine-tuning through knowledge transfer from a pre-trained model on a lar...

Why do classifier accuracies show linear trends under distribution shift?

Several recent studies observed that when classification models are eval...

Scaling Laws for Transfer

We study empirical scaling laws for transfer learning between distributi...

A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning

Adversarial Training (AT) with Projected Gradient Descent (PGD) is an ef...

LQF: Linear Quadratic Fine-Tuning

Classifiers that are linear in their parameters, and trained by optimizi...

Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance

Models for natural language understanding (NLU) tasks often rely on the ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.