Locally Pareto-Optimal Interpretations for Black-Box Machine Learning Models
This work addresses the scalability limitations in generating Pareto-optimal interpretations for black-box models, which is important for improving trustworthiness in AI applications, though it is incremental as it builds on existing multi-objective techniques.
The paper tackles the problem of synthesizing interpretations for black-box machine learning models by balancing accuracy and explainability, developing a framework that uses local optimality guarantees to achieve scalable synthesis, and demonstrates that it yields interpretations closely matching those from methods with global guarantees.
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.