Semantic Scholar Open Access 2020 132 sitasi

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

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

Abstrak

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.

Topik & Kata Kunci

Computer Science

Penulis (4)

Ashraf Abdul

C. von der Weth

Mohan Kankanhalli

Brian Y. Lim

Format Sitasi

APA MLA BibTeX

Abdul, A., Weth, C.v.d., Kankanhalli, M., Lim, B.Y. (2020). COGAM: Measuring and Moderating Cognitive Load in Machine Learning Model Explanations. https://doi.org/10.1145/3313831.3376615

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →

Lihat di Sumber doi.org/10.1145/3313831.3376615

Informasi Jurnal

Tahun Terbit: 2020
Bahasa: en
Total Sitasi: 132×
Sumber Database: Semantic Scholar
DOI: 10.1145/3313831.3376615
Akses: Open Access ✓