RESQUE: Quantifying Estimator to Task and Distribution Shift for Sustainable Model Reusability

TL;DR

RESQUE is a predictive index that estimates the retraining cost of deep learning models under distributional shifts or task changes, aiding sustainable model reuse by providing a single resource requirement measure.

Contribution

This paper introduces RESQUE, a novel estimator that quantifies retraining costs for models facing distribution or task shifts, facilitating sustainable and cost-effective model reuse.

Findings

RESQUE correlates strongly with retraining measures like epochs and energy.

It effectively predicts resource needs across various noise types and intensities.

RESQUE supports informed decisions for sustainable model retraining.

Abstract

As a strategy for sustainability of deep learning, reusing an existing model by retraining it rather than training a new model from scratch is critical. In this paper, we propose REpresentation Shift QUantifying Estimator (RESQUE), a predictive quantifier to estimate the retraining cost of a model to distributional shifts or change of tasks. It provides a single concise index for an estimate of resources required for retraining the model. Through extensive experiments, we show that RESQUE has a strong correlation with various retraining measures. Our results validate that RESQUE is an effective indicator in terms of epochs, gradient norms, changes of parameter magnitude, energy, and carbon emissions. These measures align well with RESQUE for new tasks, multiple noise types, and varying noise intensities. As a result, RESQUE enables users to make informed decisions for retraining to different tasks/distribution shifts and determine the most cost-effective and sustainable option, allowing for the reuse of a model with a much smaller footprint in the environment. The code for this work is available here: https://github.com/JEKimLab/AAAI2025RESQUE