A Shapley Value Estimation Speedup for Efficient Explainable Quantum AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Burge, Iain, Barbeau, Michel, Garcia-Alfaro, Joaquin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917987358867456
author Burge, Iain
Barbeau, Michel
Garcia-Alfaro, Joaquin
author_facet Burge, Iain
Barbeau, Michel
Garcia-Alfaro, Joaquin
contents This work focuses on developing efficient post-hoc explanations for quantum AI algorithms. In classical contexts, the cooperative game theory concept of the Shapley value adapts naturally to post-hoc explanations, where it can be used to identify which factors are important in an AI's decision-making process. An interesting question is how to translate Shapley values to the quantum setting and whether quantum effects could be used to accelerate their calculation. We propose quantum algorithms that can extract Shapley values within some confidence interval. Our method is capable of quadratically outperforming classical Monte Carlo approaches to approximating Shapley values up to polylogarithmic factors in various circumstances. We demonstrate the validity of our approach empirically with specific voting games and provide rigorous proofs of performance for general cooperative games.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14639
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Shapley Value Estimation Speedup for Efficient Explainable Quantum AI
Burge, Iain
Barbeau, Michel
Garcia-Alfaro, Joaquin
Quantum Physics
Artificial Intelligence
Cryptography and Security
This work focuses on developing efficient post-hoc explanations for quantum AI algorithms. In classical contexts, the cooperative game theory concept of the Shapley value adapts naturally to post-hoc explanations, where it can be used to identify which factors are important in an AI's decision-making process. An interesting question is how to translate Shapley values to the quantum setting and whether quantum effects could be used to accelerate their calculation. We propose quantum algorithms that can extract Shapley values within some confidence interval. Our method is capable of quadratically outperforming classical Monte Carlo approaches to approximating Shapley values up to polylogarithmic factors in various circumstances. We demonstrate the validity of our approach empirically with specific voting games and provide rigorous proofs of performance for general cooperative games.
title A Shapley Value Estimation Speedup for Efficient Explainable Quantum AI
topic Quantum Physics
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2412.14639