[3E5-GS-2] Machine learning: Explainable AI (2)

[3E5-GS-2-01] Neural Generators of Sparse Local Linear Models

〇Yuya Yoshikawa¹, Tomoharu Iwata² (1. Chiba Institute of Technology, 2. NTT)

Keywords:Interpretability, Deep learning, Local linear models

For reliability, it is important that the predictions made by machine learning methods are interpretable by human.
To combine both the benefits of the high predictive performance of deep neural networks (DNNs) and high interpretability of linear models into a single model, we propose neural generators of sparse local linear models (NGSLLs).
The sparse local linear models have high flexibility as they can approximate non-linear functions.
The NGSLL generates sparse linear weights for each sample using DNNs
that take original representations of each sample and their simplified representations as input.
By extracting features from the original representations, the weights can contain rich information to achieve high predictive performance.
Additionally, the prediction is interpretable because it is obtained by the inner product between the simplified representations and the sparse weights, where only a small number of weights are selected by our gate module in the NGSLL.
In experiments on an image classification task, we demonstrate the effectiveness of the NGSLL quantitatively and qualitatively by evaluating prediction performance and visualizing generated weights.