Aggregate Representation Measure for Predictive Model Reusability

Published: 21 Oct 2023, Last Modified: 15 Dec 2023NeurIPS CompSust 2023 PosterEveryoneRevisionsBibTeX
Keywords: quantitative resource predictor, model reusability, distributional shift, sustainability
Abstract: In this paper, we propose a predictive quantifier to estimate the retraining cost of a trained model in distribution shifts. The proposed Aggregated Representation Measure (ARM) quantifies the change in the model's representation from the old to new data distribution. It provides, before actually retraining the model, a single concise index of resources - epochs, energy, and carbon emissions - required for the retraining. This enables reuse of a model with a much lower cost than training a new model from scratch. The experimental results indicate that ARM reasonably predicts retraining costs for varying noise intensities and enables comparisons among multiple model architectures to determine the most cost-effective and sustainable option.
Submission Number: 16