Joint Explainability-Performance Optimization With Surrogate Models for AI-Driven Edge Services
This work addresses the need for reliable and explainable AI in edge computing, offering an incremental improvement in balancing performance and interpretability.
The paper tackled the trade-off between predictive accuracy and explainability in AI models for edge services by proposing a joint training scheme using multi-objective optimization, achieving over 99% fidelity in surrogate model approximation with less than 3% reduction in accuracy compared to baselines.
Explainable AI is a crucial component for edge services, as it ensures reliable decision making based on complex AI models. Surrogate models are a prominent approach of XAI where human-interpretable models, such as a linear regression model, are trained to approximate a complex (black-box) model's predictions. This paper delves into the balance between the predictive accuracy of complex AI models and their approximation by surrogate ones, advocating that both these models benefit from being learned simultaneously. We derive a joint (bi-level) training scheme for both models and we introduce a new algorithm based on multi-objective optimization (MOO) to simultaneously minimize both the complex model's prediction error and the error between its outputs and those of the surrogate. Our approach leads to improvements that exceed 99% in the approximation of the black-box model through the surrogate one, as measured by the metric of Fidelity, for a compromise of less than 3% absolute reduction in the black-box model's predictive accuracy, compared to single-task and multi-task learning baselines. By improving Fidelity, we can derive more trustworthy explanations of the complex model's outcomes from the surrogate, enabling reliable AI applications for intelligent services at the network edge.