# InstaSHAP: Interpretable Additive Models Explain Shapley Values Instantly

arXiv: https://arxiv.org/abs/2502.14177 · HTML: https://mlsanity.com/paper/2502.14177/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2025.

## Built on by (most cited first, 9 of 9)

- [SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelism](https://mlsanity.com/paper/2510.21599/) (2025)
- [Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions](https://mlsanity.com/paper/2508.05430/) (2025)
- [Additive Models Explained: A Computational Complexity Approach](https://mlsanity.com/paper/2510.21292/) (2025)
- [Informative Post-Hoc Explanations Only Exist for Simple Functions](https://mlsanity.com/paper/2508.11441/) (2025)
- [KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning](https://mlsanity.com/paper/2602.03034/) (2026)
- [Provably Explaining Neural Additive Models](https://mlsanity.com/paper/2602.17530/) (2026)
- [Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks](https://mlsanity.com/paper/2605.24084/) (2026)
- [OperatorSHAP: Fast and Accurate Shapley Value Estimation for Neural Operators](https://mlsanity.com/paper/2606.28065/) (2026)
- [Cross-seed explainability using Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoders](https://mlsanity.com/paper/2607.08499/) (2026)

## Abstract (arXiv)

In recent years, the Shapley value and SHAP explanations have emerged as one of the most dominant paradigms for providing post-hoc explanations of black-box models. Despite their well-founded theoretical properties, many recent works have focused on the limitations in both their computational efficiency and their representation power. The underlying connection with additive models, however, is left critically under-emphasized in the current literature. In this work, we find that a variational perspective linking GAM models and SHAP explanations is able to provide deep insights into nearly all recent developments. In light of this connection, we borrow in the other direction to develop a new method to train interpretable GAM models which are automatically purified to compute the Shapley value in a single forward pass. Finally, we provide theoretical results showing the limited representation power of GAM models is the same Achilles' heel existing in SHAP and discuss the implications for SHAP's modern usage in CV and NLP.