Inverse Optimality for Fair Digital Twins: A Preference-based approach

TL;DR

This paper introduces a preference-based framework for integrating fairness into Digital Twins, enabling decisions that better align with human perceptions of fairness in complex socio-technical systems.

Contribution

It proposes a novel learning workflow using a Siamese neural network to infer fairness objectives from human preferences, improving the alignment of autonomous decisions with human values.

Findings

Effective in a COVID-19 hospital resource allocation scenario

Generates fairness-aware decisions with computational efficiency

Bridges the gap between optimality and human expectations

Abstract

Digital Twins (DTs) are increasingly used as autonomous decision-makers in complex socio-technical systems. However, their mathematically optimal decisions often diverge from human expectations, revealing a persistent mismatch between algorithmic and bounded human rationality. This work addresses this challenge by proposing a framework that introduces fairness as a learnable objective within optimization-based Digital Twins. In this respect, a preference-driven learning workflow that infers latent fairness objectives directly from human pairwise preferences over feasible decisions is introduced. A dedicated Siamese neural network is developed to generate convex quadratic cost functions conditioned on contextual information. The resulting surrogate objectives drive the optimization procedure toward solutions that better reflect human-perceived fairness while maintaining computational efficiency. The effectiveness of the approach is demonstrated on a COVID-19 hospital resource allocation scenario. Overall, this work offers a practical solution to integrate human-centered fairness into the design of autonomous decision-making systems.