Locally Pareto-Optimal Interpretations for Black-Box Machine Learning Models

2025-08-21

AI Summary

Existing Pareto-optimal explanation methods for black-box model interpretability either lack formal guarantees or suffer from severe scalability bottlenecks, hindering the simultaneous achievement of accuracy and interpretability. Method: We propose a multi-objective explanation synthesis framework grounded in local optimality verification. It formulates local Pareto-optimality certification as a Boolean satisfiability (SAT) problem and integrates multi-objective Monte Carlo tree search for efficient, bounded-depth optimization—obviating exhaustive global search. Contribution/Results: Our approach provides rigorous formal guarantees on local Pareto optimality while achieving explanation quality comparable to global Pareto-optimal methods. Empirical evaluation across multiple benchmark datasets demonstrates both high explanation fidelity and superior scalability. By enabling verifiable, computationally tractable local explanations, the framework establishes a new paradigm for trustworthy AI that bridges theoretical soundness with practical deployability.

Technology Category

• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Search and Optimization: Local Search
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Creating meaningful interpretations for black-box machine learning models involves balancing two often conflicting objectives: accuracy and explainability. Exploring the trade-off between these objectives is essential for developing trustworthy interpretations. While many techniques for multi-objective interpretation synthesis have been developed, they typically lack formal guarantees on the Pareto-optimality of the results. Methods that do provide such guarantees, on the other hand, often face severe scalability limitations when exploring the Pareto-optimal space. To address this, we develop a framework based on local optimality guarantees that enables more scalable synthesis of interpretations. Specifically, we consider the problem of synthesizing a set of Pareto-optimal interpretations with local optimality guarantees, within the immediate neighborhood of each solution. Our approach begins with a multi-objective learning or search technique, such as Multi-Objective Monte Carlo Tree Search, to generate a best-effort set of Pareto-optimal candidates with respect to accuracy and explainability. We then verify local optimality for each candidate as a Boolean satisfiability problem, which we solve using a SAT solver. We demonstrate the efficacy of our approach on a set of benchmarks, comparing it against previous methods for exploring the Pareto-optimal front of interpretations. In particular, we show that our approach yields interpretations that closely match those synthesized by methods offering global guarantees.

Problem

• Balancing accuracy and explainability in black-box model interpretations
• Synthesizing Pareto-optimal interpretations with local optimality guarantees
• Addressing scalability limitations in Pareto-optimal interpretation synthesis

Innovation

• Local Pareto-optimality guarantees for interpretations
• Multi-Objective Monte Carlo Tree Search generation
• SAT solver verification of Boolean satisfiability