Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

VIOLET: Visual Analytics for Explainable Quantum Neural Networks (2312.15276v1)

Published 23 Dec 2023 in cs.HC and quant-ph

Abstract: 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

Definition Search Book Streamline Icon: https://streamlinehq.com
References (86)
  1. Suppressing quantum errors by scaling a surface code logical qubit. Nature, 614(7949):676–681, 2023. doi: 10 . 1038/s41586-022-05434-1
  2. M. Altaisky. Quantum neural network. arXiv preprint quant-ph/0107012, 2001.
  3. Multiple-qubit quantum state visualization. In Proceedings of 2009 Conference on Lasers and Electro-Optics and 2009 Conference on Quantum electronics and Laser Science Conference, pp. 1–2. IEEE, 2009. doi: 10 . 1364/IQEC . 2009 . IWC1
  4. Quantum supremacy using a programmable superconducting processor. Nature, 574(7779):505–510, 2019. doi: 10 . 1038/s41586-019-1666-5
  5. Simulation of quantum-state endoscopy. Physical Review A, 53(4):2736, 1996.
  6. J. Bausch. Recurrent quantum neural networks. Advances in Neural Information Processing Systems, 33:1368–1379, 2020.
  7. Training deep quantum neural networks. Nature Communications, 11(1):808, 2020.
  8. Erratum: parameterized quantum circuits as machine learning models. Quantum Science and Technology, 5(1):019601, 2019.
  9. Quantum information and computation. Nature, 404(6775):247–255, 2000.
  10. A. Blance and M. Spannowsky. Quantum machine learning for particle physics using a variational quantum classifier. Journal of High Energy Physics, 2021(2):1–20, 2021.
  11. F. Bloch. Nuclear induction. Physical Review, 70(7-8):460, 1946. doi: 10 . 1103/PhysRev . 70 . 460
  12. Variational quantum algorithms. Nature Reviews Physics, 3(9):625–644, 2021.
  13. Challenges and opportunities in quantum machine learning. Nature Computational Science, 2(9):567–576, 2022. doi: 10 . 1038/s43588-022-00311-3
  14. I. Chalkiadakis. A brief survey of visualization methods for deep learning models from the perspective of explainable ai. 2018.
  15. Digitized counterdiabatic quantum algorithm for protein folding. Physical Review Applied, 20(1):014024, 2023.
  16. Hybrid quantum-classical classifier based on tensor network and variational quantum circuit. arXiv preprint arXiv:2011.14651, 2020.
  17. VBridge: Connecting the dots between features and data to explain healthcare models. IEEE Transactions on Visualization and Computer Graphics, 28(1):378–388, 2021.
  18. J. Choo and S. Liu. Visual analytics for explainable deep learning. IEEE Computer Graphics and Applications, 38(4):84–92, 2018.
  19. Re-vacnn: Steering convolutional neural network via real-time visual analytics. In Proceedings of Future of Interactive Learning Machines Workshop at the 30th Annual Conference on Neural Information Processing Systems, 2016.
  20. A. Daskin. On the explainability of quantum neural networks based on variational quantum circuits. arXiv preprint arXiv:2301.05549, 2023.
  21. Y. Ding and A. Javadi-Abhari. Quantum and post-moore’s law computing. IEEE Internet Computing, 26(1):5–6, 2022. doi: 10 . 1109/MIC . 2021 . 3133675
  22. R. Fong and A. Vedaldi. Net2Vec: Quantifying and explaining how concepts are encoded by filters in deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8730–8738, 2018.
  23. M. Galambos and S. Imre. Visualizing the effects of measurements and logic gates on multi-qubit systems using fractal representation. International Journal on Advances in Systems and Measurements, 5(1), 2012.
  24. Quantum computing: Computational excellence for society 5.0. 2021.
  25. Explaining quantum circuits with shapley values: Towards explainable quantum machine learning. 2023.
  26. Summit: Scaling deep learning interpretability by visualizing activation and attribution summarizations. IEEE Transactions on Visualization and Computer Graphics, 26(1):1096–1106, 2019.
  27. Near-term quantum computing techniques: Variational quantum algorithms, error mitigation, circuit compilation, benchmarking and classical simulation. Science China Physics, Mechanics & Astronomy, 66(5):250302, 2023.
  28. Variational quantum tensor networks classifiers. Neurocomputing, 452:89–98, 2021. doi: 10 . 1016/j . neucom . 2021 . 04 . 074
  29. Evaluation of parameterized quantum circuits: on the relation between classification accuracy, expressibility, and entangling capability. Quantum Machine Intelligence, 3:1–19, 2021.
  30. IBMQ Phase Disk. https://learning.quantum-computing.ibm.com/tutorial/composer-user-guide#phase-disk/, Access Date: 2023-11-23.
  31. Quantum neural network states: A brief review of methods and applications. Advanced Quantum Technologies, 2(7-8):1800077, 2019.
  32. Gnnlens: A visual analytics approach for prediction error diagnosis of graph neural networks. IEEE Transactions on Visualization and Computer Graphics, 2022.
  33. Activis: Visual exploration of industry-scale deep neural network models. IEEE Transactions on Visualization and Computer Graphics, 24(1):88–97, 2017.
  34. Gan lab: Understanding complex deep generative models using interactive visual experimentation. IEEE Transactions on Visualization and Computer Graphics, 25(1):310–320, 2018.
  35. Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets. Nature, 549(7671):242–246, 2017.
  36. I. G. Karafyllidis. Visualization of the quantum fourier transform using a quantum computer simulator. Quantum Information Processing, 2:271–288, 2003.
  37. M. Keyl. Fundamentals of quantum information theory. Physics Reports, 369(5):431–548, 2002.
  38. W. Li and D.-L. Deng. Recent advances for quantum classifiers. Science China Physics, Mechanics & Astronomy, 65(2):220301, 2022. doi: 10 . 1007/s11433-021-1793-6
  39. Quantum neural network classifiers: A tutorial. SciPost Physics Lecture Notes, p. 061, 2022.
  40. Deeptracker: Visualizing the training process of convolutional neural networks. ACM Transactions on Intelligent Systems and Technology, 10(1), nov 2018. doi: 10 . 1145/3200489
  41. Towards better analysis of deep convolutional neural networks. IEEE Transactions on Visualization and Computer Graphics, 23(1):91–100, 2016.
  42. Towards better analysis of machine learning models: A visual analytics perspective. Visual Informatics, 1(1):48–56, 2017.
  43. Visualizing graph neural networks with corgie: Corresponding a graph to its embedding. IEEE Transactions on Visualization and Computer Graphics, 28(6):2500–2516, 2022.
  44. Variational quantum classifier for binary classification: Real vs synthetic dataset. IEEE Access, 10:3705–3715, 2021. doi: 10 . 1109/ACCESS . 2021 . 3139323
  45. H. Mäkelä and A. Messina. N-qubit states as points on the bloch sphere. Physica Scripta, 2010(T140):014054, 2010. doi: 10 . 1088/0031-8949/2010/T140/014054
  46. Rulematrix: Visualizing and understanding classifiers with rules. IEEE Transactions on Visualization and Computer Graphics, 25(1):342–352, 2018. doi: 10 . 1109/TVCG . 2018 . 2864812
  47. A multidisciplinary survey and framework for design and evaluation of explainable ai systems. ACM Transactions on Interactive Intelligent Systems (TiiS), 11(3-4):1–45, 2021.
  48. T. Munzner. A nested model for visualization design and validation. IEEE Transactions on Visualization and Computer Graphics, 15(6):921–928, 2009. doi: 10 . 1109/TVCG . 2009 . 111
  49. Quantum computation and quantum information. Cambridge University Press, 2010.
  50. Quantum computing: progress and prospects. National Academies Press, 2019.
  51. A tutorial on quantum convolutional neural networks (qcnn). In Proceedings of 2020 International Conference on Information and Communication Technology Convergence (ICTC), pp. 236–239. IEEE, 2020. doi: 10 . 1109/ICTC49870 . 2020 . 9289439
  52. Feature visualization. Distill, 2(11):e7, 2017.
  53. Paddle Quantum: quantum classifier. https://qml.baidu.com/tutorials/machine-learning/quantum-classifier.html, Access Date: 2023-8-28.
  54. Neurocartography: Scalable automatic visual summarization of concepts in deep neural networks. IEEE Transactions on Visualization and Computer Graphics, 28(1):813–823, 2022. doi: 10 . 1109/TVCG . 2021 . 3114858
  55. I. Piatrenka and M. Rusek. Quantum variational multi-class classifier for the iris data set. In Proceedings of International Conference on Computational Science, pp. 247–260. Springer, 2022.
  56. J. Preskill. Quantum computing in the nisq era and beyond. Quantum, 2:79, 2018. doi: 10 . 22331/q-2018-08-06-79
  57. Quantum Neural Networks. https://qiskit.org/ecosystem/machine-learning/tutorials/01_neural_networks.html, Access Date: 2023-8-30.
  58. How to efficiently handle complex values? Implementing decision diagrams for quantum computing. In 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), pp. 1–7. IEEE, 2019.
  59. Quantum computing: A gentle introduction. MIT Press, 2011.
  60. Quantumeyes: Towards better interpretability of quantum circuits. IEEE Transactions on Visualization & Computer Graphics, (01):1–13, 2023.
  61. VACSEN: A Visualization Approach for Noise Awareness in Quantum Computing. IEEE Transactions on Visualization and Computer Graphics, 29(1):462–472, 2022. doi: 10 . 1109/TVCG . 2022 . 3209455
  62. VENUS: A Geometrical Representation for Quantum State Visualization. In Computer Graphics Forum, vol. 42, pp. 247–258. Wiley Online Library, 2023. doi: 10 . 1111/cgf . 14827
  63. Integrating data and model space in ensemble learning by visual analytics. IEEE Transactions on Big Data, 7(3):483–496, 2018.
  64. Circuit-centric quantum classifiers. Physical Review A, 101(3):032308, 2020. doi: 10 . 1103/PhysRevA . 101 . 032308
  65. M. Schuld and N. Killoran. Quantum machine learning in feature hilbert spaces. Physical Review Letters, 122(4):040504, 2019.
  66. Design study methodology: Reflections from the trenches and the stacks. IEEE Transactions on Visualization and Computer Graphics, 18(12):2431–2440, 2012.
  67. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626, 2017.
  68. Dfseer: A visual analytics approach to facilitate model selection for demand forecasting. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, pp. 1–13, 2020.
  69. Learning temporal data with a variational quantum recurrent neural network. Physical Review A, 103(5):052414, 2021.
  70. Recent advances for quantum neural networks in generative learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023. doi: 10 . 1109/TPAMI . 2023 . 3272029
  71. TorchQuantum. https://github.com/mit-han-lab/torchquantum, Access Date: 2023-8-28.
  72. Nas-navigator: Visual steering for explainable one-shot deep neural network synthesis. IEEE Transactions on Visualization and Computer Graphics, 1912.
  73. G. Vilone and L. Longo. Explainable artificial intelligence: a systematic review. arXiv preprint arXiv:2006.00093, 2020.
  74. Atmseer: Increasing transparency and controllability in automated machine learning. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, pp. 1–12, 2019.
  75. Visual analysis of discrimination in machine learning. IEEE Transactions on Visualization and Computer Graphics, 27(2):1470–1480, 2020.
  76. M2Lens: Visualizing and explaining multimodal models for sentiment analysis. IEEE Transactions on Visualization and Computer Graphics, 28(1):802–812, 2021.
  77. Exploration of quantum neural architecture by mixing quantum neuron designs. In Proceedings of 2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD), pp. 1–7. IEEE, 2021.
  78. Quantum deep learning. arXiv preprint arXiv:1412.3489, 2014.
  79. M. M. Wilde. Quantum information theory. Cambridge University Press, 2013.
  80. Visualizing decision diagrams for quantum computing (special session summary). In Proceedings of 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 768–773. IEEE, 2021. doi: 10 . 23919/DATE51398 . 2021 . 9474236
  81. M. M. Williams. QCVis: A quantum circuit visualization and education platform for novices. PhD thesis, Harvard University, 2021.
  82. Interactive correction of mislabeled training data. In Proceedings of 2019 IEEE Conference on Visual Analytics Science and Technology (VAST), pp. 57–68. IEEE, 2019.
  83. Diagnosing ensemble few-shot classifiers. IEEE Transactions on Visualization and Computer Graphics, 28(9):3292–3306, 2022.
  84. Cnncomparator: Comparative analytics of convolutional neural networks. arXiv preprint arXiv:1710.05285, 2017.
  85. Y. Zhang and Q. Ni. Recent advances in quantum machine learning. Quantum Engineering, 2(1):e34, 2020. doi: 10 . 1002/que2 . 34
  86. Quantum neural network for quantum neural computing. Research, 6:0134, 2023.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now