Special Session 4:
Quantum Machine Learning
Algorithms and Applications
In recent years, quantum computing has undergone remarkable advancements, progressing from its inception in the 1980s to the emergence of hardware prototypes in the 2020s capable of managing hundreds of qubits. Despite being in its nascent stage, the swift progress in both quantum hardware and algorithms has sparked discussions regarding the potential supremacy of Noisy-Intermediate Scale Quantum (NISQ) devices over classical computers. Among the plethora of algorithms proposed for NISQ devices, the Variational Quantum Eigensolver (VQE) stands out as particularly promising. It showcases the ability to function effectively with a limited number of qubits while demonstrating resilience to noise.
Classified as hybrid quantum-classical methodologies, VQE algorithms facilitate the practical utilization of Variational Quantum Circuits (VQC), seamlessly merging classical machine learning and artificial intelligence frameworks. Particularly noteworthy is VQC's versatility in constructing Quantum Neural Networks (QNNs), which have found success in various applications. These include quantum convolutional neural networks (QCNNs) for image classification, quantum generative adversarial networks (QGANs) for image reconstruction, quantum long short-term memory (QLSTM) models for tasks such as time-series modeling and natural language processing, and quantum reinforcement learning (QRL) for intricate sequential decision-making processes. These approaches present a holistic framework that capitalizes on the respective strengths of both quantum and classical computation.
In this context, our proposal aims to conduct an in-depth exploration of VQC-based Quantum Machine Learning (QML) algorithms, pushing the boundaries of state-of-the-art QML and investigating their applications in the domains of machine learning and artificial intelligence problems.
This special session invites submissions of various types of QML papers, encompassing fundamental training algorithms, trustworthy and privacy-preserving QML, and a broad range of application scenarios in both scientific discovery and commercial & industrial applications.
Scope and topics:
Topics relevant to this session include, but are not limited to:
- Quantum machine learning in the context of trustworthy ML (e.g. differential pricacy, federated learning)
- Quantum machine learning with an emphasis on cybersecurity
- Quantum machine learning in speech and natural language processing
- Quantum machine learning for scientific discovery
- Quantum machine learning for commercial and industrial applications
- Quantum machine learning systems
Chairs: Samuel Yen-Chi Chen, Muhammad Ismail, Ying Mao, Khoa Luu, Huan-Hsin Tseng, Shinjae Yoo
Bio:
Samuel Yen-Chi Chen received the Ph.D. and B.S. degree in physics from National Taiwan University, Taipei City, Taiwan. He is now a senior research scientist at Wells Fargo Bank. Prior to that, he was an assistant computational scientist in the Computational Science Initiative, Brookhaven National Laboratory. He is the first one to use variational quantum circuits to perform deep reinforcement learning and the inventor of quantum LSTM. His research interests include building quantum machine learning algorithms as well as applying classical machine learning techniques to solve quantum computing problems. He won the First Prize in the Software Competition (Research Category) from Xanadu Quantum Technologies, in 2019. Dr. Chen is a seasoned speaker renowned for his expertise in delivering tutorials on quantum machine learning at prestigious conferences. Notably, he has presented tutorial talks on leveraging quantum neural networks for speech and natural language processing at IJCAI 2021 and ICASSP 2022. At ICASSP 2024 and IJCNN 2024, Dr. Chen expanded on this knowledge, providing tutorials on the integration of quantum tensor networks and quantum neural networks for signal processing in machine learning. Moreover, he shared insights into quantum machine learning and its applications in 6G communication at IEEE ICC 2024. In addition, Dr. Chen is frequently invited to deliver talks and tutorials on related topics in various events. For example, Dr. Chen delivered a talk about Hybrid Quantum-Classical Machine Learning in ND-MIT Quantum Computer Systems Lecture Series, Washington DC Quantum Computing meetup, AQT Seminars at Lawrence Berkeley National Lab and Quantum Information Summit at American University of Beirut. Dr. Chen also presented various topics in QML in conferences such as ICASSP, IEEE QCE, QTML, NeurIPS and IJCNN.Email:ycchen1989@ieee.org
Dr. Huan Hsin Tseng is a research scientist at the Computational Science Initiative of the Brookhaven National Lab. He received a Ph.D. and a B.S. degree in Physics and Mathematics from National Tsing Hua University. His background was in High Energy Physics, General Relativity, and Quantum Fields in Spacetime. Previously, he was with the University of Michigan, Ann Arbor, working on RL radiotherapy cancer treatments. He was also with the Academia Sinica under Dr. Yu Tsao�s Lab conducting research on deep speech analysis and deep speech enhancement. He currently conducts projects on Quantum multi-chip integration with classical systems, generalization of VQC and general Quantum Machine Learning. His current interests focus on AI/ML, Quantum Computing, and their intersections. Email:htseng@bnl.gov
Dr. Muhammad Ismail (Senior Member, IEEE) received the B.Sc. (Hons.) and M.Sc. degrees in electrical engineering (electronics and communications) from Ain Shams University, Cairo, Egypt, in 2007 and 2009, respectively, and the Ph.D. degree in electrical and computer engineering from the University of Waterloo, Waterloo, ON, Canada, in 2013. He is currently an Associate Professor with the Department of Computer Science, Tennessee Technological University, Cookeville, TN, USA. He was a co-recipient of the best paper awards in the IEEE ICC 2014, the IEEE GLOBECOM 2014, the SGRE 2015 and 2024, the Green 2016, the IEEE IS 2020, and the Best Conference Paper Award from the IEEE Communications Society Technical Committee on Green Communications and Networking for his publication in IEEE ICC 2019. He delivered several tutorials on various topics in flagship IEEE conferences such as IEEE HPSR (2022), IEEE SmartGridComm (2020), IEEE WCNC (2016), and IEEE Globecom (2015). He was the TPC Track Co-Chair of the IEEE SmartGridComm 2023, Workshop Co-Chair of the IEEE Greencom 2018, the TPC Track Co-Chair of the IEEE VTC 2017 and 2016, the Publicity and Publication CoChair of the CROWNCOM 2015, and the Web-Chair of the IEEE INFOCOM 2014. He was an Associate Editor of IET Communications, PHYCOM, and the IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING. He was an Editorial Assistant of the IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, from 2011 to 2013. He is an Associate Editor of the IEEE INTERNET OF THINGS JOURNAL and the IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY. He has been a technical reviewer of several IEEE conferences and journals. Dr. Ismail has taught courses in classical and quantum machine learning. Part of his research team focuses on the applications of quantum information science in machine learning, networking, and security. Email:mismail@tntech.edu
Prof. Ying Mao is an Associate Professor and associate chair for undergraduate studies in the Department of Computer and Information Science at Fordham University in New York City. He earned his Master of Science in Electrical Engineering from the University at Buffalo in 2011. He received his Ph.D. in Computer Science from the University of Massachusetts Boston in 2016. He was a Fordham-IBM research fellow. His research interests mainly focus on the fields of quantum systems, quantum-classical co-optimization, quantum machine learning, quantum system virtualization, cloud resource management, data-intensive platforms, and containerized applications. His research has been supported by multiple grants from the National Science Foundation, Google Research, NVIDIA, and Microsoft. Email:ymao41@fordham.edu
Prof. Khoa Luu is a Tenure-track Assistant Professor and the
Director of the Computer Vision and Image Understanding
(CVIU) Lab in the Department of Electrical Engineering
and Computer Science at the University of Arkansas (UA),
Fayetteville. He is affiliated with the NSF MonARK Quantum
Foundry. He is an Associate Editor of the IEEE Access Journal
and the Multimedia Tools and Applications Journal, Springer
Nature. He is also the Area Chair in the IEEE/CVF Conference
on Computer Vision and Pattern Recognition (CVPR), 2023
and 2024, and the Conference on Neural Information Processing Systems (NeurIPS) 2024. He was the Research Project
Director at the Cylab Biometrics Center at Carnegie Mellon
University (CMU), US. His research interests focus on various
topics, including Quantum Machine Learning, Robot Vision,
Vision-Language Learning, Deep Generative Modeling and
Compressed Sensing. He has received six patents, and three
best paper awards and coauthored 120+ papers in conferences,
technical reports, and journals. He was a vice-chair of the
Montreal Chapter IEEE SMCS in Canada from September
2009 to March 2011. He is the Technical Program Chair
of the IEEE GreenTech Conference 2024, the chair of the
CVPR Precognition Workshop in 2019-2024, and the MICCAI
Workshop in 2019 and 2020. He was a PC member of AAAI,
ICPRAI in 2020 and 2022, and IJCAI-ECAI in 2022.Email:khoaluu
Dr. Shinjae Yoo is a senior research scientist at the Computational Science Initiative of the Brookhaven National Lab. He received his Master's and Ph.D. in Language Technologies from Carnegie Mellon University and a B.S. degree in Computer Science from Soongsil University. His background was in natural language processing and machine learning. His current interests focus on scientific machine learning, streaming analysis, distributed computing, quantum information science, quantum machine learning, and the intersection of them. Email:sjyoo@bnl.gov
Technical Committee
- Samuel Yen-Chi Chen, Wells Fargo Bank, USA
- Huan-Hsin Tseng, Brookhaven National Laboratory, USA
- Ying Mao, Fordham University, USA
- Khoa Luu, University of Arkansas, USA
- Shinjae Yoo, Brookhaven National Laboratory, USA
- Muhammad Ismail, Tennessee Tech University, USA
Paper Submission Instructions
All papers will be double-blind reviewed and must present original work.
- CMT Submission Site
- Select the track: Special Session 3: Machine Learning for Predictive Models in Engineering Applications
Papers submitted for reviewing should conform to IEEE specifications. Manuscript templates can be downloaded from:
Keydates
- Submission due date: September 9, 2024
- Notification of Acceptance: September 25, 2024
- Camera Ready Papers: October 5, 2024
- Pre-registration: October 15, 2024
- Conference: December 18-20, 2024
Registration
In order for your paper to be presented in the virtual session and published in the proceedings you must register to the conference.
Paper Presentation Instructions
The papers submitted to this track will be presented in person as part of the conference. There is no virtual presentation for this session.
ICMLA'24