Saved in:
Bibliographic Details
Main Authors: Charalampakos, Foivos, Tsouparopoulos, Thomas, Koutsopoulos, Iordanis
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.07784
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909532982083584
author Charalampakos, Foivos
Tsouparopoulos, Thomas
Koutsopoulos, Iordanis
author_facet Charalampakos, Foivos
Tsouparopoulos, Thomas
Koutsopoulos, Iordanis
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_07784
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Joint Explainability-Performance Optimization With Surrogate Models for AI-Driven Edge Services
Charalampakos, Foivos
Tsouparopoulos, Thomas
Koutsopoulos, Iordanis
Machine Learning
Artificial Intelligence
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.
title Joint Explainability-Performance Optimization With Surrogate Models for AI-Driven Edge Services
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2503.07784