ANOVA-NODE: An identifiable neural network for the functional ANOVA model for better interpretability

Seokhun Park, Insung Kong, yongchan Choi, Chanmoo Park, Yongdai Kim

Keywords: Interpretability, Explianability, Trustworthy AI, Functional ANOVA model, Generalized additive models

TL;DR: In this paper, we propose a new neural network model which guarantees a unique functional ANOVA decomposition and thus is able to estimate each component stably.

Abstract:

Interpretability for machine learning models is becoming more and more important as machine learning models become more complex.
The functional ANOVA model, which decomposes a high-dimensional function into a sum of lower dimensional functions so called components, is one of the most popular tools for interpretable AI, and recently, various neural network models have been developed for estimating each component in the functional ANOVA model.
However, such neural networks are highly unstable when estimating components since the components themselves are not uniquely defined.
That is, there are multiple functional ANOVA decompositions for a given function.
In this paper, we propose a novel interpretable model which guarantees a unique functional ANOVA decomposition and thus is able to estimate each component stably.
We call our proposed model ANOVA-NODE since it is a modification of Neural Oblivious Decision Ensembles (NODE) for the functional ANOVA model.
Theoretically, we prove that ANOVA-NODE can approximate a smooth function well.
Additionally, we experimentally show that ANOVA-NODE provides much more stable estimation of each component and thus much more stable interpretation when training data and initial values of the model parameters vary than existing neural network models do.

Primary Area: interpretability and explainable AI

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 10220