Quantum Machine Learning for Intelligent ICT Systems: A Survey of Models, Algorithms, Challenges, and Future Directions

Abstract

Quantum machine learning (QML) is an emerging research area that combines quantum computing with machine learning to exploit quantum superposition, entanglement, interference, and high-dimensional Hilbert-space representations. This paper presents a concise survey of QML models and algorithms for near-term noisy intermediate-scale quantum (NISQ) devices and future fault-tolerant quantum computers. Representative QML approaches are reviewed, including quantum feature maps, quantum kernel methods, variational quantum classifiers, quantum neural networks, quantum convolutional neural networks, and quantum generative learning. In addition, the paper discusses how QML can be connected with intelligent information and communication technology (ICT) systems, including semantic communications, wireless networking, UAV-assisted systems, metaverse services, non-terrestrial networks, and autonomous mobility. Finally, key open challenges are summarized, including data loading, hardware noise, barren plateaus, scalability, benchmarking fairness, and the need for practical quantum advantage.