Skip to content

Regional Explanations via Causal Sufficiency and Necessity

Sep 2026 · 0 citations · 42 references
Computer Science

TL;DR

Causal Sufficient and Necessary Regional Explanations (SNRE), a framework that learns an input region and output region such that membership in A is both sufficient and necessary for the model output to fall in B, is proposed.

Abstract

Model explainability is essential for understanding and trusting machine learning models. Existing explainable AI methods often explain predictions through feature importance, counterfactual explanations, or rules. However, a region-level characterization of when and only when a prediction behavior arises remains less explored. This paper proposes Causal Sufficient and Necessary Regional Explanations (SNRE), a framework that learns an input region $A$ and output region $B$ such that membership in $A$ is both sufficient and necessary for the model output to fall in $B$. Motivated by the classical Probability of Necessity and Sufficiency (PNS), we formulate a region-level PNS measure through stochastic interventions and derive a differentiable finite-sample estimator for optimization. SNRE parameterizes the input-output region pair with explicit and interpretable algebraic region families, together with a learnable feature mask, balancing expressiveness and interpretability. Experiments demonstrate that SNRE learns region pairs with strong sufficiency-necessity performance, robust explanation behavior, and practical utility for model analysis.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

A Computationally Feasible Framework for Causal Probabilistic Explanation

Probabilistic Causal Impact (PCI) builds on actual causality and on Pearl's notions of probability of necessity and sufficiency, but recasts the question of explainability as an estimation problem on a probabilistic causal model that is easily approximated via Monte Carlo.

R. Urbaniak, Sam Witty, Daniel Waxman et al. · 1 citation
Preprint Aug 2026

Evidence, Calibration, and Stability: A Triadic Framework for Hypothesis Testing Under Model Uncertainty

Statistical tests are often asked to do too much. A single reported result is expected to describe what the observed data say, reassure readers about repeated-sampling behavior, and remain convincing when the working model is perturbed. Those tasks are connected, but they are not equivalent. Fisherian inductive inferen...

Subir Hait · 0 citations
#artificial intelligence Preprint Sep 2026

Probabilistic Linear Explanations

This work presents a unified framework for probabilistic explainability based on sparse, anchored linear models, applicable to both binary classification and continuous regression, and addresses the resulting empirical problem using a Mixed Integer Programming formulation that yields provably optimal empirical solution...

F. Koriche, Jean-Marie Lagniez, Chi Tran · 0 citations
#machine learning Preprint Sep 2026

The Statistical Cost of Causal Discovery with Feedback

What determines the unavoidable sample cost of learning cyclic causal structure? For cyclic linear non-Gaussian models, we study exact condensation recovery from observational data: identifying the strongly connected component (SCC) partition and all edges between components. We establish the first information-theoreti...

Sunmin Oh, Seung-Su Han, Gunwoong Park · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.