Search Results for author:
Found 6 papers, 2 papers with code
Energy and Carbon Considerations of Fine-Tuning BERT
Despite the popularity of the `pre-train then fine-tune' paradigm in the NLP community, existing work quantifying energy costs and associated carbon emissions has largely focused on language model pre-training.
Shapley Residuals: Quantifying the limits of the Shapley value for explanations
Popular feature importance techniques compute additive approximations to nonlinear models by first defining a cooperative game describing the value of different subsets of the model's features, then calculating the resulting game's Shapley values to attribute credit additively between the features.
Problems with Shapley-value-based explanations as feature importance measures
Game-theoretic formulations of feature importance have become popular as a way to "explain" machine learning models.
Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data
Then, we illustrate the usefulness of both algorithms as a combined method for training models from a few data points on new tasks while using Fairness Warnings as interpretable boundary conditions under which the newly trained model may not be fair.
