Synthesizing Pareto-Optimal Interpretations for Black-Box Models

by   Hazem Torfah, et al.

We present a new multi-objective optimization approach for synthesizing interpretations that "explain" the behavior of black-box machine learning models. Constructing human-understandable interpretations for black-box models often requires balancing conflicting objectives. A simple interpretation may be easier to understand for humans while being less precise in its predictions vis-a-vis a complex interpretation. Existing methods for synthesizing interpretations use a single objective function and are often optimized for a single class of interpretations. In contrast, we provide a more general and multi-objective synthesis framework that allows users to choose (1) the class of syntactic templates from which an interpretation should be synthesized, and (2) quantitative measures on both the correctness and explainability of an interpretation. For a given black-box, our approach yields a set of Pareto-optimal interpretations with respect to the correctness and explainability measures. We show that the underlying multi-objective optimization problem can be solved via a reduction to quantitative constraint solving, such as weighted maximum satisfiability. To demonstrate the benefits of our approach, we have applied it to synthesize interpretations for black-box neural-network classifiers. Our experiments show that there often exists a rich and varied set of choices for interpretations that are missed by existing approaches.



page 1


BMOBench: Black-Box Multi-Objective Optimization Benchmarking Platform

This document briefly describes the Black-Box Multi-Objective Optimizati...

An Interpretable Probabilistic Approach for Demystifying Black-box Predictive Models

The use of sophisticated machine learning models for critical decision m...

Learning outside the Black-Box: The pursuit of interpretable models

Machine Learning has proved its ability to produce accurate models but t...

Interpretation of Neural Networks is Fragile

In order for machine learning to be deployed and trusted in many applica...

Programming by Rewards

We formalize and study “programming by rewards” (PBR), a new approach fo...

Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates

Among the most critical limitations of deep learning NLP models are thei...

Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimization

Single-objective black box optimization (also known as zeroth-order opti...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.