Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions

09/30/2022
by   Minkyu Kim, et al.
0

Black-box models, such as deep neural networks, exhibit superior predictive performances, but understanding their behavior is notoriously difficult. Many explainable artificial intelligence methods have been proposed to reveal the decision-making processes of black box models. However, their applications in high-stakes domains remain limited. Recently proposed neural additive models (NAM) have achieved state-of-the-art interpretable machine learning. NAM can provide straightforward interpretations with slight performance sacrifices compared with multi-layer perceptron. However, NAM can only model 1^st-order feature interactions; thus, it cannot capture the co-relationships between input features. To overcome this problem, we propose a novel interpretable machine learning method called higher-order neural additive models (HONAM) and a feature interaction method for high interpretability. HONAM can model arbitrary orders of feature interactions. Therefore, it can provide the high predictive performance and interpretability that high-stakes domains need. In addition, we propose a novel hidden unit to effectively learn sharp-shape functions. We conducted experiments using various real-world datasets to examine the effectiveness of HONAM. Furthermore, we demonstrate that HONAM can achieve fair AI with a slight performance sacrifice. The source code for HONAM is publicly available.

READ FULL TEXT

page 14

page 15

research
05/27/2022

Neural Basis Models for Interpretability

Due to the widespread use of complex machine learning models in real-wor...
research
06/04/2019

An interpretable machine learning framework for modelling human decision behavior

Machine learning has recently been widely adopted to address the manager...
research
06/05/2021

Constrained Generalized Additive 2 Model with Consideration of High-Order Interactions

In recent years, machine learning and AI have been introduced in many in...
research
09/21/2023

Regionally Additive Models: Explainable-by-design models minimizing feature interactions

Generalized Additive Models (GAMs) are widely used explainable-by-design...
research
05/27/2022

Scalable Interpretability via Polynomials

Generalized Additive Models (GAMs) have quickly become the leading choic...
research
01/20/2020

An interpretable neural network model through piecewise linear approximation

Most existing interpretable methods explain a black-box model in a post-...
research
08/24/2021

Predicting Census Survey Response Rates via Interpretable Nonparametric Additive Models with Structured Interactions

Accurate and interpretable prediction of survey response rates is import...

Please sign up or login with your details

Forgot password? Click here to reset