# CAT: Interpretable Concept-based Taylor Additive Models

arXiv: https://arxiv.org/abs/2406.17931 · HTML: https://mlsanity.com/paper/2406.17931/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 47 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Neural Additive Models: Interpretable Machine Learning with Neural Nets](https://mlsanity.com/paper/2004.13912/) (2020)
- [Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding](https://mlsanity.com/paper/1810.02338/) (2018)
- [Concept Whitening for Interpretable Image Recognition](https://mlsanity.com/paper/2002.01650/) (2020)
- [Model-Agnostic Interpretability of Machine Learning](https://mlsanity.com/paper/1606.05386/) (2016)
- [Post-hoc Interpretability for Neural NLP: A Survey](https://mlsanity.com/paper/2108.04840/) (2021)
- [Promises and Pitfalls of Black-Box Concept Learning Models](https://mlsanity.com/paper/2106.13314/) (2021)
- [Reliable Post hoc Explanations: Modeling Uncertainty in Explainability](https://mlsanity.com/paper/2008.05030/) (2020)
- [NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning](https://mlsanity.com/paper/2106.01613/) (2021)
- [Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off](https://mlsanity.com/paper/2209.09056/) (2022)
- [Neural Basis Models for Interpretability](https://mlsanity.com/paper/2205.14120/) (2022)
- [Interpretability Beyond Classification Output: Semantic Bottleneck Networks](https://mlsanity.com/paper/1907.10882/) (2019)
- [Global and Local Interpretability for Cardiac MRI Classification](https://mlsanity.com/paper/1906.06188/) (2019)
- [Semantic bottleneck for computer vision tasks](https://mlsanity.com/paper/1811.02234/) (2018)

## Built on by (most cited first, 5 of 5)

- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity](https://mlsanity.com/paper/2602.10585/) (2026)
- [ParamBoost: Gradient Boosted Piecewise Cubic Polynomials](https://mlsanity.com/paper/2604.18864/) (2026)
- [Meta Additive Model: Interpretable Sparse Learning With Auto Weighting](https://mlsanity.com/paper/2604.20111/) (2026)
- [Traffic-CBM: A Structurally Interpretable Multimodal Framework for Encrypted Traffic Classification](https://mlsanity.com/paper/2606.29909/) (2026)

## Abstract (arXiv)

As an emerging interpretable technique, Generalized Additive Models (GAMs) adopt neural networks to individually learn non-linear functions for each feature, which are then combined through a linear model for final predictions. Although GAMs can explain deep neural networks (DNNs) at the feature level, they require large numbers of model parameters and are prone to overfitting, making them hard to train and scale. Additionally, in real-world datasets with many features, the interpretability of feature-based explanations diminishes for humans. To tackle these issues, recent research has shifted towards concept-based interpretable methods. These approaches try to integrate concept learning as an intermediate step before making predictions, explaining the predictions in terms of human-understandable concepts. However, these methods require domain experts to extensively label concepts with relevant names and their ground-truth values. In response, we propose CAT, a novel interpretable Concept-bAsed Taylor additive model to simply this process. CAT does not have to require domain experts to annotate concepts and their ground-truth values. Instead, it only requires users to simply categorize input features into broad groups, which can be easily accomplished through a quick metadata review. Specifically, CAT first embeds each group of input features into one-dimensional high-level concept representation, and then feeds the concept representations into a new white-box Taylor Neural Network (TaylorNet). The TaylorNet aims to learn the non-linear relationship between the inputs and outputs using polynomials. Evaluation results across multiple benchmarks demonstrate that CAT can outperform or compete with the baselines while reducing the need of extensive model parameters. Importantly, it can explain model predictions through high-level concepts that human can understand.