Neural Basis Models for InterpretabilityDownload PDF

Published: 31 Oct 2022, 18:00, Last Modified: 20 Oct 2022, 21:32NeurIPS 2022 AcceptReaders: Everyone
Keywords: interpretability, explainability, trustworthy AI, interpretable machine learning, generalized additive models
TL;DR: We propose a novel subfamily of GAMs that utilizes basis decomposition of shape functions, called Neural Basis Models (NBMs). NBMs exploit the feature correlations and allow GAMs to scale by order of magnitude while preserving the interpretability.
Abstract: Due to the widespread use of complex machine learning models in real-world applications, it is becoming critical to explain model predictions. However, these models are typically black-box deep neural networks, explained post-hoc via methods with known faithfulness limitations. Generalized Additive Models (GAMs) are an inherently interpretable class of models that address this limitation by learning a non-linear shape function for each feature separately, followed by a linear model on top. However, these models are typically difficult to train, require numerous parameters, and are difficult to scale. We propose an entirely new subfamily of GAMs that utilizes basis decomposition of shape functions. A small number of basis functions are shared among all features, and are learned jointly for a given task, thus making our model scale much better to large-scale data with high-dimensional features, especially when features are sparse. We propose an architecture denoted as the Neural Basis Model (NBM) which uses a single neural network to learn these bases. On a variety of tabular and image datasets, we demonstrate that for interpretable machine learning, NBMs are the state-of-the-art in accuracy, model size, and, throughput and can easily model all higher-order feature interactions. Source code is available at \href{}{\ttfamily}.
Supplementary Material: zip
15 Replies