COGAM: Measuring and Moderating Cognitive Load in Machine Learning Model Explanations

By Ashraf Abdul, C. von der Weth, Mohan Kankanhalli, Brian Y. Lim. 2020

138 citations recorded by the source corpus.

Interpretable machine learning models trade -off accuracy for simplicity to make explanations more readable and easier to comprehend. Drawing from cognitive psychology theories in graph comprehension, we formalize readability as visual cognitive chunks to measure and moderate the cognitive load in explanation visualizations. We present Cognitive-GAM (COGAM) to generate explanations with desired cognitive load and accuracy by combining the expressive nonlinear generalized additive models (GAM) with simpler sparse linear models. We calibrated visual cognitive chunks with reading time in a user study, characterized the trade-off between cognitive load and accuracy for four datasets in simulation studies, and evaluated COGAM against baselines with users. We found that COGAM can decrease cognitive load without decreasing accuracy and/or increase accuracy without increasing cognitive load. Our framework and empirical measurement instruments for cognitive load will enable more rigorous assessment of the human interpretability of explainable AI.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Manipulating and Measuring Model Interpretability (2018, background): “8We emphasize that we are referring to visual information overload that affects attention to items on a display [19], not cognitive load in working memory, which has also been shown to be related to interpretability [1, 60].”
Are Explanations Helpful? A Comparative Study of the Effects of Explanations in AI-Assisted Decision-Making (2021, methodology): “To this end, techniques for presenting explanations visually, selectively, and progressively [54, 62, 69], and methods for incorporating the consideration of cognitive load into the explanation generation process [1] should be explored.”
Human-Centered Explainable AI (XAI): From Algorithms to User Experiences (2021, background): “Technical approaches that optimize for a balance between explanation accuracy and conciseness have also been explored [5].”
Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies (2021, methodology): “The shape function of GAMs is used to inspect the global feature importance for GAMs.”