Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

JustQ: Automated Deployment of Fair and Accurate Quantum Neural Networks

Ruhan Wang, Fahiz Baba-Yara, Fan Chen

TL;DR

This work pioneers fair QNN design on NISQ computers, paving the way for future investigations and proposes JustQ, a framework for deploying fair and accurate QNNs on NISQ computers.

Abstract

Despite the success of Quantum Neural Networks (QNNs) in decision-making systems, their fairness remains unexplored, as the focus primarily lies on accuracy. This work conducts a design space exploration, unveiling QNN unfairness, and highlighting the significant influence of QNN deployment and quantum noise on accuracy and fairness. To effectively navigate the vast QNN deployment design space, we propose JustQ, a framework for deploying fair and accurate QNNs on NISQ computers. It includes a complete NISQ error model, reinforcement learning-based deployment, and a flexible optimization objective incorporating both fairness and accuracy. Experimental results show JustQ outperforms previous methods, achieving superior accuracy and fairness. This work pioneers fair QNN design on NISQ computers, paving the way for future investigations.

JustQ: Automated Deployment of Fair and Accurate Quantum Neural Networks

TL;DR

This work pioneers fair QNN design on NISQ computers, paving the way for future investigations and proposes JustQ, a framework for deploying fair and accurate QNNs on NISQ computers.

Abstract

Despite the success of Quantum Neural Networks (QNNs) in decision-making systems, their fairness remains unexplored, as the focus primarily lies on accuracy. This work conducts a design space exploration, unveiling QNN unfairness, and highlighting the significant influence of QNN deployment and quantum noise on accuracy and fairness. To effectively navigate the vast QNN deployment design space, we propose JustQ, a framework for deploying fair and accurate QNNs on NISQ computers. It includes a complete NISQ error model, reinforcement learning-based deployment, and a flexible optimization objective incorporating both fairness and accuracy. Experimental results show JustQ outperforms previous methods, achieving superior accuracy and fairness. This work pioneers fair QNN design on NISQ computers, paving the way for future investigations.
Paper Structure (15 sections, 6 equations, 10 figures, 2 tables)

This paper contains 15 sections, 6 equations, 10 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Preliminary
  3. NISQ Hardware
  4. Quantum Neural Networks
  5. Reinforcement Learning
  6. Design Space Exploration
  7. Design Space Complexity
  8. Fairness and Accuracy in Synthesized QNNs
  9. JustQ
  10. The JustQ Framework
  11. The JustQ Error Model and Measurement
  12. RL-based QNN Deployment
  13. Experimental Methodology
  14. Results and Analysis
  15. Conclusion

Figures (10)

  • Figure 1: A standard QNN and its approximate synthesis.
  • Figure 2: (a) Output distance and (b) accuracy of synthesized QNNs on IBM_Almaden (HPW: hours-per-week, Edu: education; CapG: capital-gain).
  • Figure 3: QNN fairness vs. (a) CNOT gate # and (b) circuit depth; QNN accuracy vs. (c) CNOT gate # and (d) circuit depth.
  • Figure 4: A standard DQL model.
  • Figure 5: The JustQ framework. Left: the overall architecture. Middle and Right: functional blocks in JustQ: (a) state generator; (b) reward generator.
  • ...and 5 more figures