A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity
Recent advancements have highlighted the limitations of current quantum systems, particularly the restricted number of qubits available on near-term quantum devices. This constraint greatly inhibits the range of applications that can leverage quantum computers. Moreover, as the available qubits incr...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Transactions on Quantum Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10439653/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586881599012864 |
|---|---|
| author | Ryan L'Abbate Anthony D'Onofrio Samuel Stein Samuel Yen-Chi Chen Ang Li Pin-Yu Chen Juntao Chen Ying Mao |
| author_facet | Ryan L'Abbate Anthony D'Onofrio Samuel Stein Samuel Yen-Chi Chen Ang Li Pin-Yu Chen Juntao Chen Ying Mao |
| author_sort | Ryan L'Abbate |
| collection | DOAJ |
| description | Recent advancements have highlighted the limitations of current quantum systems, particularly the restricted number of qubits available on near-term quantum devices. This constraint greatly inhibits the range of applications that can leverage quantum computers. Moreover, as the available qubits increase, the computational complexity grows exponentially, posing additional challenges. Consequently, there is an urgent need to use qubits efficiently and mitigate both present limitations and future complexities. To address this, existing quantum applications attempt to integrate classical and quantum systems in a hybrid framework. In this article, we concentrate on quantum deep learning and introduce a collaborative classical-quantum architecture called co-TenQu. The classical component employs a tensor network for compression and feature extraction, enabling higher dimensional data to be encoded onto logical quantum circuits with limited qubits. On the quantum side, we propose a quantum-state-fidelity-based evaluation function to iteratively train the network through a feedback loop between the two sides. co-TenQu has been implemented and evaluated with both simulators and the IBM-Q platform. Compared to state-of-the-art approaches, co-TenQu enhances a classical deep neural network by up to 41.72% in a fair setting. In addition, it outperforms other quantum-based methods by up to 1.9 times and achieves similar accuracy while utilizing 70.59% fewer qubits. |
| format | Article |
| id | doaj-art-afc9a3f62d624867913f4949f271a034 |
| institution | Kabale University |
| issn | 2689-1808 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Quantum Engineering |
| spelling | doaj-art-afc9a3f62d624867913f4949f271a0342025-01-25T00:03:26ZengIEEEIEEE Transactions on Quantum Engineering2689-18082024-01-01511410.1109/TQE.2024.336723410439653A Quantum-Classical Collaborative Training Architecture Based on Quantum State FidelityRyan L'Abbate0https://orcid.org/0009-0007-8296-6288Anthony D'Onofrio1https://orcid.org/0009-0002-8362-024XSamuel Stein2https://orcid.org/0000-0002-2655-8251Samuel Yen-Chi Chen3https://orcid.org/0000-0003-0114-4826Ang Li4https://orcid.org/0000-0003-3734-9137Pin-Yu Chen5https://orcid.org/0000-0003-1039-8369Juntao Chen6https://orcid.org/0000-0001-7726-4926Ying Mao7https://orcid.org/0000-0002-4484-4892Computer and Information Science Department, Fordham University, Bronx, NY, USAComputer and Information Science Department, Fordham University, Bronx, NY, USAPacific Northwest National Laboratory, Richland, WA, USABrookhaven National Laboratory, Upton, NY, USAPacific Northwest National Laboratory, Richland, WA, USAIBM Research, Yorktown Heights, NY, USAComputer and Information Science Department, Fordham University, Bronx, NY, USAComputer and Information Science Department, Fordham University, Bronx, NY, USARecent advancements have highlighted the limitations of current quantum systems, particularly the restricted number of qubits available on near-term quantum devices. This constraint greatly inhibits the range of applications that can leverage quantum computers. Moreover, as the available qubits increase, the computational complexity grows exponentially, posing additional challenges. Consequently, there is an urgent need to use qubits efficiently and mitigate both present limitations and future complexities. To address this, existing quantum applications attempt to integrate classical and quantum systems in a hybrid framework. In this article, we concentrate on quantum deep learning and introduce a collaborative classical-quantum architecture called co-TenQu. The classical component employs a tensor network for compression and feature extraction, enabling higher dimensional data to be encoded onto logical quantum circuits with limited qubits. On the quantum side, we propose a quantum-state-fidelity-based evaluation function to iteratively train the network through a feedback loop between the two sides. co-TenQu has been implemented and evaluated with both simulators and the IBM-Q platform. Compared to state-of-the-art approaches, co-TenQu enhances a classical deep neural network by up to 41.72% in a fair setting. In addition, it outperforms other quantum-based methods by up to 1.9 times and achieves similar accuracy while utilizing 70.59% fewer qubits.https://ieeexplore.ieee.org/document/10439653/Collaborative trainingquantum deep learningquantum-classical hybrid systems |
| spellingShingle | Ryan L'Abbate Anthony D'Onofrio Samuel Stein Samuel Yen-Chi Chen Ang Li Pin-Yu Chen Juntao Chen Ying Mao A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity IEEE Transactions on Quantum Engineering Collaborative training quantum deep learning quantum-classical hybrid systems |
| title | A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity |
| title_full | A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity |
| title_fullStr | A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity |
| title_full_unstemmed | A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity |
| title_short | A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity |
| title_sort | quantum classical collaborative training architecture based on quantum state fidelity |
| topic | Collaborative training quantum deep learning quantum-classical hybrid systems |
| url | https://ieeexplore.ieee.org/document/10439653/ |
| work_keys_str_mv | AT ryanlabbate aquantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT anthonydonofrio aquantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT samuelstein aquantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT samuelyenchichen aquantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT angli aquantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT pinyuchen aquantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT juntaochen aquantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT yingmao aquantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT ryanlabbate quantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT anthonydonofrio quantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT samuelstein quantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT samuelyenchichen quantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT angli quantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT pinyuchen quantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT juntaochen quantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity AT yingmao quantumclassicalcollaborativetrainingarchitecturebasedonquantumstatefidelity |