---
title: Shapley Interaction Indices (SIIs)
url: https://www.emergentmind.com/topics/shapley-interaction-indices-siis
type: topic
---

# Shapley Interaction Indices (SIIs)

Shapley Interaction Indices (SIIs) are a class of functionals originating in cooperative game theory that quantify the effect of interactions among subsets of players (or, equivalently, features or variables in a model) on a model’s output or a game’s value. Unlike the classical Shapley value, which allocates payoff to individuals, SIIs decompose the total value into attributions not only to single elements but also to interacting groups, allowing the nuanced identification and measurement of synergistic, redundant, or antagonistic effects within coalitions. SIIs are foundational to modern sensitivity analysis, feature attribution in machine learning, multi-criteria aggregation, and collective decision-making frameworks. Their computation, theoretical properties, axiomatic characterizations, and practical estimation strategies have been the subject of intensive research, resulting in a variety of indices, approximators, and application algorithms.

## 1. Mathematical Foundations and Core Definitions

SIIs generalize the Shapley value by assigning indices $I_T(f)$ to every non-empty subset $T \subseteq N$ (the set of players or features), capturing the additional value attributable specifically to the interaction among elements of $T$. For a set function $f: 2^N \rightarrow \mathbb{R}$, the most studied SII, introduced by Grabisch and Roubens, is defined by:

\[
I_T(f) = \sum_{S \subseteq N \setminus T} \frac{(n - |S| - |T|)! \, |S|!}{(n - |T| + 1)!} \left[ \Delta_T f(S) \right]
\]

where $\Delta_T f(S) = \sum_{K \subseteq T} (-1)^{|T|-|K|} f(S \cup K)$ is the discrete derivative or finite difference w.r.t. the subset $T$.

SIIs obey three foundational axioms for any cardinal interaction index: linearity (the index is linear in $f$), symmetry (labels of elements are exchangeable), and the dummy axiom (indices for coalitions containing dummy elements vanish). Under these axioms, the SII is uniquely determined [2303.01179], with alternative forms corresponding to different weightings or combinatorial averaging schemes.

A significant insight is that the Shapley value for a singleton recovers the main effect; higher-order indices correspond to interaction among subsets, allowing a Taylor-type expansion of $f$ over its subsets [1902.05622].

## 2. Axiomatic Extensions and Generalizations

While the standard Shapley interaction index satisfies linearity, symmetry, and dummy axioms, it does not enforce efficiency, i.e., the sum of all attributions does not necessarily equal the total function difference $f(N) - f(\varnothing)$ [1902.05622]. The Shapley–Taylor index remedies this by adding an interaction distribution axiom, resulting in an index akin to a truncated Taylor expansion of the multilinear extension of $f$:

- For $|S| < k$, the index for subset $S$ is the discrete derivative at $\varnothing$.
- For $|S| = k$, the index takes the average over all orderings, recapitulating the Lagrange remainder term of a Taylor series [1902.05622].

Alternatively, the Faithful Shapley Interaction Index (Faith–Shap) is defined as the unique solution to a weighted least squares problem over polynomial approximations, enforcing efficiency while eschewing less natural recursion or interaction distribution axioms, yielding a principled allocation of effects across interaction orders [2203.00870].

Joint Shapley values [2107.11357] and n-Shapley values [2209.04012] provide further generalizations; joint Shapley values assign scores to coalitions as units, and n-Shapley values interpolate classical Shapley explanations and full additive decompositions, with explicit recovery of generalized additive model terms.

## 3. Computation and Algorithmic Advances

Exact computation of SIIs involves evaluating $f$ on all $2^n$ subsets and is exponential in $n$ [2303.01179]. Key algorithms and approximators have been developed:

- **Möbius Inverse Formula:** Reformulates the SII using the Möbius coefficients of $f$, allowing expressions such as:

\[
I_T(f) = \sum_{S \supseteq T} a(S) / |S|
\]

with $a(S)$ being Möbius coefficients [2002.12024]. This yields significant computational savings (from $k! \cdot k$ to $2^k$ for $k$ inputs).

- **Sampling Algorithms:** Monte Carlo methods leverage sampling over random permutations or subsets to estimate SIIs, often using explicit variance bounds and unbiasedness assertions [2303.01179], [2401.13371], [2402.04774].
  - SVARM-IQ uses a stratified representation of the coalition space, partitioned by intersection size and coalition cardinality, enabling maximal sample reuse and rapid convergence [2401.13371].
  - SHAP-IQ provides a unified, unbiased, and variance-controlled approximation applicable to any cardinal interaction index; it closely matches or outperforms permutation-based and kernel least-squares methods.

- **Weighted Approximations:** In sensitivity analysis contexts, SIIs can be computed via weighted least squares fits, as for the Banzhaf or Shapley interaction indices, which are interpretable as averages (centers of mass) over suitably defined probability spaces for coalition formation [1001.3052].

In specific models, such as KNN classifiers, structure-exploiting algorithms (e.g., STI-KNN) reduce complexity from $O(2^n)$ to $O(t n^2)$ by exploiting linearity and ordering symmetries within the valuation function [2304.01224].

## 4. SIIs in Sensitivity Analysis and Statistical Modeling

SIIs have been integrated into global sensitivity analysis as “Shapley effects” [1707.01334], [1801.03300]. In this vein:

- **Variance Decomposition:** SIIs allocate output variance to groups of input variables in models where standard ANOVA (Sobol indices) may be ill-defined, e.g., with correlated inputs.
  - For linear Gaussian models, closed-form computation is possible via analytical conditional variances [1801.04095].
  - In nonlinear or empirical scenarios, Gaussian linear approximations provide provably convergent estimators under mild assumptions [2006.02087].

- **Reliability-Oriented Sensitivity Analysis:** Target Shapley effects assign sensitivity scores not to continuous outputs but to binary or thresholded events (e.g., failure probabilities in risk models), preserving efficiency and interpretability in multivariate risk allocation frameworks [2101.08083].

- **Practical Algorithms:** Efficient estimation leverages metamodels (e.g., kriging surrogates) and resampling for computationally intensive simulations [1707.01334], [1801.03300].

In GSA, SIIs facilitate factor prioritization/fixing and provide robustness to statistical dependence, outperforming classical Sobol indices in interpretability for correlated settings.

## 5. Interpretability, Feature Attribution, and Applications in AI

SIIs are central to feature attribution in explainable AI:

- **Attribution Decomposition:** SIIs describe not only individual feature effects but also quantify joint interactions (e.g., synergy, redundancy, antagonism) across any order [1902.05622], [2209.04012]. For instance, the Shapley–Taylor index recovers key interaction patterns in sentiment models, regression, and context-dependent question answering tasks.

- **Model Alignment:** n-Shapley Values and similar indices reveal the extent to which a machine learning model is functionally decomposable into generalized additive components or requires explicit interaction modeling. This supports precise diagnostic and visualization tools [2209.04012].

- **Data Valuation:** In data valuation, pairwise SIIs for training points can be computed efficiently via problem-specific algorithms, helping with summarization, acquisition, and outlier detection [2304.01224].

- **Joint Feature Importance:** Joint Shapley values directly address the contribution of coalitions (as opposed to the distributed interaction terms in other indices), providing novel insights into group-level impact, particularly with binary features or structured attribution tasks [2107.11357].

- **Fuzzy Measures and Aggregation Operators:** SIIs and their sampling-based estimators underpin advanced aggregation techniques (e.g., the Choquet integral, fuzzy measures aggregation), capturing non-additive dependencies among criteria [2402.04774].

## 6. Developments in Approximation and Computational Efficiency

Recent research has yielded multiple efficient, theoretically supported approximation strategies:

- **k-Additive Surrogate Games:** SVA$_{k_{\text{ADD}}}$ fits a surrogate game where only interactions up to order $k$ are allowed, reducing parameterization to polynomial in $n$ and enabling rapid least squares-based Shapley value estimation [2502.04763].
- **Stratification and Optimized Sampling:** SVARM-IQ and related methods exploit variance reduction via stratified coalition partitioning, often achieving state-of-the-art estimation error with dramatically fewer function evaluations [2401.13371].
- **Order-Based Representations:** Polynomial-time estimators using order (permutation)-averaged marginal contributions generalize the classical Shapley value and interaction computation, permitting unbiased, variance-controlled estimation even in high-dimensional settings [2402.04774].

These approaches have made feasible the application of SIIs in real-world industrial, ML, and statistical modeling scenarios where model evaluations are costly or the underlying combinatorics prohibit exhaustive calculation.

## 7. Conceptual Integration and Current Research Directions

Ongoing work investigates the axiomatic tradeoffs among linearity, symmetry, dummy, efficiency, and recursive or distributional interaction axioms, leading to diverse indices (Shapley–Taylor, Faith–Shap, classic SII). There is active exploration of:

- Efficient estimation in high dimensions,
- Variable order interaction indices,
- Extensions for reliability-oriented, probabilistic, or decision-theoretic sensitivity analysis,
- Integration with GAM-based decomposition and functional analysis [2209.04012],
- Comparative performance across model classes and data-generating processes.

A plausible implication is that further conceptual unification, computational innovation, and empirical validation of SIIs will continue to advance their role in interpretable modeling, robust sensitivity analysis, and equitable resource attribution within complex systems.

Source: https://www.emergentmind.com/topics/shapley-interaction-indices-siis