SMiLE: Provably Enforcing Global Relational Properties in Neural Networks

TL;DR

This paper extends the SMiLE framework to enforce global relational properties in neural networks, providing full guarantees and scalability across various properties and models, with competitive accuracy and runtime.

Contribution

It introduces a scalable, general approach for enforcing global relational properties in neural networks with provable guarantees, surpassing existing local or limited methods.

Findings

Supports global properties like robustness and fairness

Achieves full satisfaction guarantees

Competitive accuracy and runtime on synthetic and real data

Abstract

Artificial Intelligence systems are increasingly deployed in settings where ensuring robustness, fairness, or domain-specific properties is essential for regulation compliance and alignment with human values. However, especially on Neural Networks, property enforcement is very challenging, and existing methods are limited to specific constraints or local properties (defined around datapoints), or fail to provide full guarantees. We tackle these limitations by extending SMiLE, a recently proposed enforcement framework for NNs, to support global relational properties (defined over the entire input space). The proposed approach scales well with model complexity, accommodates general properties and backbones, and provides full satisfaction guarantees. We evaluate SMiLE on monotonicity, global robustness, and individual fairness, on synthetic and real data, for regression and classification tasks. Our approach is competitive with property-specific baselines in terms of accuracy and runtime, and strictly superior in terms of generality and level of guarantees. Overall, our results emphasize the potential of the SMiLE framework as a platform for future research and applications.