Generating Samples to Question Trained Models
This work addresses the problem of model interpretability for machine learning practitioners and researchers, providing an incremental approach to understanding how models operate.
This work tackles the problem of understanding trained machine learning models by generating samples that question their data preferences, with the result being a mathematical framework that can probe models and identify preferred samples. The framework is applied to various models and tasks, including classification and regression.
There is a growing need for investigating how machine learning models operate. With this work, we aim to understand trained machine learning models by questioning their data preferences. We propose a mathematical framework that allows us to probe trained models and identify their preferred samples in various scenarios including prediction-risky, parameter-sensitive, or model-contrastive samples. To showcase our framework, we pose these queries to a range of models trained on a range of classification and regression tasks, and receive answers in the form of generated data.