- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The paper argues for interpreting a model with an additive model and compare their method to SHAP. Therein, the method is to just fit a linear model (the unconstrained way, in comparison to SHAP) on the coalitions. The main claim of this paper is that this can be done easier and quicker in comparison to standard SHAP estimation via KernelSHAP.
Critical strengths
- Lemma 1 (Fourth-moment bound under Shapley sampling) seems to be a novel result, which can help with Kong & Valiant (2018)'s approach.
- Important issue: Making model interpretability more efficient is an important research area. This is particularly true for Shapley-based explanations, as they require an exponential number of subset evaluations for computing ground-truth attribution scores.
- The paper submitted the code for its experiments, which is a good thing.
Critical weaknesses
In my opinion this paper contains many weaknesses, which makes me argue clearly for rejection.
- The theoretical and methodological contribution of this work is very limited: This paper is basically just an application of Kong & Valiant (2018), a 2018 NeurIPS paper, to interpretability. While this may be an interesting avenue for interpretability, this work does not make a clear case for it. The main contribution here is an additional Lemma to the original results. But it is not clear how any of this work is relevant for the existing literature on more-efficient Shapley computations. First, the topic of better approximations is studied a lot (e.g. [4] and [5] for recent examples) but not at all positioned here in this paper. Particularly LeverageSHAP [4], which is a refinement of KernelSHAP that proposes a selection order of the coalitions, is important for any such work studying the linear estimation of SHAP-like attribution scores. Second, the "issue" of non-linearity is the main reason why interaction-based explanation methods are proposed ([3] and [1]), which is also absent from the paper here. Importantly, FaithSHAP investigates this linear fit (or lack there off) as its main driver for defining its interactions. This is further discussed in works such as Shapley residuals [2].
- Hence, the here presented paper does not really position itself within the main literature on Shapley-based interpretability. It is unclear what the benefits and the costs are. For one, we loose efficiency in the attributions, as the here proposed method just applies the unconstrained least-squares.
- Weak baselines: Only KernelSHAP as baseline. The paper only looks at the residuals of the scores. There is no connection weather this is good or bad in terms of interpretability. While I do not think this is too important here in light of the major issues already part of the paper, but the empirical evaluation only contains 6 tabular datasets. None of which suggests much interactivity in the literature.
References:
- [1] Faith-Shap: https://jmlr.org/papers/v24/22-0202.html
- [2] Shapley Residuals: https://proceedings.neurips.cc/paper_files/paper/2021/file/dfc6aa246e88ab3e32caeaaecf433550-Paper.pdf
- [3] fANOVA-Games: https://proceedings.mlr.press/v258/fumagalli25a.html
- [4] Leverage SHAP: https://proceedings.iclr.cc/paper_files/paper/2025/file/a224ff18cc99a71751aa2b79118604da-Paper-Conference.pdf
- [5] OddSHAP: https://proceedings.mlr.press/v306/fumagalli26a.html
Questions for authors
None
The review’s summary describes our method as fitting an unconstrained linear model to obtain attribution scores more efficiently than KernelSHAP. This description does not match the proposed method.
Our paper studies a different question from efficient Shapley estimation or interaction attribution. We investigate how faithfully can an additive explanation represent a prediction, and can this representational limit be assessed efficiently? We characterize this capability by Rmax2, the optimal coefficient of determination achievable by the additive function class under the explanation setting. Unconstrained least squares defines this quantity. Our method does not fit that model or return its coefficients.
The estimator itself builds on Kong & Valiant (2018). Our main technical contribution is proving the Shapley-specific fourth-moment bound that yields an O(dlogd) model-evaluation guarantee in the high-dimensional regime. This result establishes that additive fidelity can be estimated in a regime where regression coefficients cannot be uniquely identified from the sampled equations. For regression-based attribution methods such as LeverageSHAP, incorporating the efficiency constraint leaves d−1 free parameters, requiring at least d−1 sampled equations for full column rank. Below this budget, a pseudoinverse or regularization can select a solution, but the sampled equations alone do not uniquely determine the coefficients. Our estimator avoids this identification requirement.
The experiments include OLS, CHIVE, and EigenPrism in addition to KernelSHAP. We used KernelSHAP as a simple attribution-first baseline and primarily emphasized learnability and explained-variance methods because they address our scalar estimation target. The distinction between estimating optimal fidelity and recovering coefficients motivated this selection. Nevertheless, modern SHAP estimators are relevant empirical comparisons, and we will add them to evaluate the advantage against stronger attribution-first baselines.
Interaction-based explanations are also important related work. We do not claim to be the first to recognize the representational limitations of additive explanations. Our contribution is to make this limitation actionable through a scalar fidelity diagnostic with a sublinear estimation guarantee. This addresses a preliminary question: is an additive representation sufficiently faithful, or is a richer explanation needed? Interaction methods then characterize how features jointly contribute. Our method can assess additive representability without recovering either attribution coefficients or interaction quantities, and is complementary to these methods rather than a replacement for them. We will expand the discussion of Faith-Shap, Shapley Residuals, and other interaction-based approaches to clarify their relationship to our target.