MiSS: A Logic-Driven Explanation of Minimal Sufficient Coalitions for Point Cloud Classifiers
2026-07-27 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors introduce MiSS, a new method to explain how 3D point cloud classifiers make decisions by identifying the smallest important parts of a 3D shape. MiSS works without knowing the inside workings of the classifier (black-box) and uses a smart search process to find groups of regions that are enough to keep the same prediction under small changes. They tested MiSS and found it gives more precise explanations faster than some other methods. This helps understand which parts of a 3D object the model really uses to decide.
3D point cloudclassifier explanationblack-box modelsuperpoint partitionMaxSATsufficiency reasoningModelNet40ShapeNetPointNetPointMLP
Authors
Mengda Xing, Jean-Marie Lagniez
Abstract
We present MiSS, a black-box, query-based framework for explaining 3D point cloud classifiers through perturbation-relative sufficiency reasoning. MiSS treats a superpoint partition as an interpretable abstraction layer and asks whether the original prediction can be certified from a minimal coalition of geometric regions under a specified perturbation distribution. Unlike abductive explainers that require Boolean feature spaces or white-box logical encodings of the predictor, MiSS separates candidate proposal from verification: a weighted MaxSAT procedure proposes coalitions using a heuristic adaptive cardinality floor, certified exact-size fallback, a safely tightened upper bound, blocking clauses, and a surrogate acquisition heuristic learned from previous oracle evaluations, while a blackbox statistical oracle decides sufficiency from prediction queries. The system returns a statistically verified sufficient coalition as a binary attribution, with minimum cardinality guaranteed when certified search completes. Experiments on ModelNet40 and ShapeNet with PointNet and PointMLP classifiers show higher precision and coverage than rule-based baselines in most settings, with lower explanation time than exhaustive search.