Two4Two: Evaluating Interpretable Machine Learning - A Synthetic Dataset For Controlled Experiments
This work addresses the problem of conducting rigorous human-subject evaluations for interpretable ML researchers, though it is incremental as it builds on existing synthetic data approaches.
The authors tackled the challenge of evaluating interpretable machine learning methods by creating a synthetic dataset generator that allows controlled experiments with minimal parameters, resulting in biases that are predictive for classifiers but subtle enough to be visually noticeable to only half of human participants.
A growing number of approaches exist to generate explanations for image classification. However, few of these approaches are subjected to human-subject evaluations, partly because it is challenging to design controlled experiments with natural image datasets, as they leave essential factors out of the researcher's control. With our approach, researchers can describe their desired dataset with only a few parameters. Based on these, our library generates synthetic image data of two 3D abstract animals. The resulting data is suitable for algorithmic as well as human-subject evaluations. Our user study results demonstrate that our method can create biases predictive enough for a classifier and subtle enough to be noticeable only to every second participant inspecting the data visually. Our approach significantly lowers the barrier for conducting human subject evaluations, thereby facilitating more rigorous investigations into interpretable machine learning. For our library and datasets see, https://github.com/mschuessler/two4two/