DeepAI AI Chat
Log In Sign Up

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

by   Minkyu Kim, et al.

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.


page 14

page 15


Neural Basis Models for Interpretability

Due to the widespread use of complex machine learning models in real-wor...

An interpretable machine learning framework for modelling human decision behavior

Machine learning has recently been widely adopted to address the manager...

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

In recent years, machine learning and AI have been introduced in many in...

Scalable Interpretability via Polynomials

Generalized Additive Models (GAMs) have quickly become the leading choic...

An interpretable neural network model through piecewise linear approximation

Most existing interpretable methods explain a black-box model in a post-...