Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Computational Sustainability: Promises and Pitfalls from Theory to Deployment

Aggregate Representation Measure for Predictive Model Reusability

Lokesh Vishwesh Sangarya · Richard Bradford · Jung-Eun Kim


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.

Chat is not available.