Explanation-Driven Self-Adaptation Using Model-Agnostic Interpretable Machine Learning

Self-adaptive systems increasingly rely on black-box predictive models (e.g., Neural Networks) to make decisions and steer adaptations. The lack of transparency of these models makes it hard to explain adaptation decisions and their possible effects on the surrounding environment. Furthermore, adapt...

Full description

Saved in:
Bibliographic Details
Published in:ICSE Workshop on Software Engineering for Adaptive and Self-Managing Systems (Online) pp. 189 - 199
Main Authors: Negri, Francesco Renato, Nicolosi, Niccolo, Camilli, Matteo, Mirandola, Raffaela
Format: Conference Proceeding
Language:English
Published: ACM 15.04.2024
Subjects:
Adaptation models
Closed box
Costs
Explainable Self-adaptation
Inter-pretable Machine Learning
Machine learning
Model-agnostic explanations
Neural networks
Planning
Predictive models
ISSN:2157-2321
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Self-adaptive systems increasingly rely on black-box predictive models (e.g., Neural Networks) to make decisions and steer adaptations. The lack of transparency of these models makes it hard to explain adaptation decisions and their possible effects on the surrounding environment. Furthermore, adaptation decisions in this context are typically the outcome of expensive optimization processes. The complexity arises from the inability to directly observe or comprehend the internal mechanisms of the black-box predictive models, which requires employing iterative methods to explore a possibly large search space and optimize according to many goals. Here, balancing the trade-off between effectiveness and cost becomes a crucial challenge. In this paper, we propose explanation-driven self-adaptation, a novel approach that embeds model-agnostic interpretable machine learning techniques into the feedback loop to enhance the transparency of the predictive models and gain insights that help drive adaptation decisions effectively by significantly reducing the cost of planning them. Our empirical evaluation demonstrates the cost-effectiveness of our approach using two evaluation subjects in the robotics domain.
ISSN:2157-2321
DOI:10.1145/3643915.3644085