VIOLET: Visual Analytics for Explainable Quantum Neural Networks

With the rapid development of Quantum Machine Learning, quantum neural networks (QNN) have experienced great advancement in the past few years, harnessing the advantages of quantum computing to significantly speed up classical machine learning tasks. Despite their increasing popularity, the quantum...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on visualization and computer graphics 2024-06, Vol.30 (6), p.2862-2874
Main Authors: Ruan, Shaolun, Liang, Zhiding, Guan, Qiang, Griffin, Paul, Wen, Xiaolin, Lin, Yanna, Wang, Yong
Format: Article
Language:English
Subjects:
Data visualization
explainable artificial intelligence (XAI)
Machine learning
Neural networks
Quantum circuit
Quantum computing
quantum machine learning
Quantum state
Qubit
qunatum neural networks
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the rapid development of Quantum Machine Learning, quantum neural networks (QNN) have experienced great advancement in the past few years, harnessing the advantages of quantum computing to significantly speed up classical machine learning tasks. Despite their increasing popularity, the quantum neural network is quite counter-intuitive and difficult to understand, due to their unique quantum-specific layers (e.g., data encoding and measurement) in their architecture. It prevents QNN users and researchers from effectively understanding its inner workings and exploring the model training status. To fill the research gap, we propose VIOLET , a novel visual analytics approach to improve the explainability of quantum neural networks. Guided by the design requirements distilled from the interviews with domain experts and the literature survey, we developed three visualization views: the Encoder View unveils the process of converting classical input data into quantum states, the Ansatz View reveals the temporal evolution of quantum states in the training process, and the Feature View displays the features a QNN has learned after the training process. Two novel visual designs, i.e., satellite chart and augmented heatmap, are proposed to visually explain the variational parameters and quantum circuit measurements respectively. We evaluate VIOLET through two case studies and in-depth interviews with 12 domain experts. The results demonstrate the effectiveness and usability of VIOLET in helping QNN users and developers intuitively understand and explore quantum neural networks.
ISSN:1077-2626
1941-0506
DOI:10.1109/TVCG.2024.3388557