About
My research focuses on Federated Learning and Quantum Machine Learning to enable secure, privacy-preserving intelligence across edge and distributed systems, alongside Deep Reinforcement Learning applications in tactical MANETs and wireless communications. I completed my PhD in Information Technology from Deakin University, Australia, and Master of Computer Science from the University of Wollongong.
Research Areas
1. Classical, Quantum Machine Learning
Working on classical and quantum machine learning problems that includes Variational Quantum Circuits, Quantum Neural Networks etc. using tools and platforms like Qiskit, PennyLane, TensorCircuit, TensorFlow, PyTorch, and IBM Quantum hardware.
2. Federated Learning, Quantum Federated Learning
Developing novel efficient adaptive FL/QFL frameworks to mitigate quantum circuit noise, heterogeneity, communication bottlenecks and other challenges in distributed networks.
Wireless Communication, Deep Reinforcement Learning
Study and exploration of wireless communications, deep reinforcement learning, tactical MANETs, and AI-enabled wireless technologies.
Selected Publications
View All 16 Publications →First QFL framework to jointly analyze training efficiency, structured personalization, and test generalization under non-IID conditions with a 50% communication reduction.
Adaptive network service management distilling locally fine-tuned LLMs into autonomous network agents to optimize client selection and early stopping in QFL.
Comprehensive survey and empirical benchmark comparing major quantum software libraries on simulators against physical IBM Quantum Hardware.
Serverless chained continuous QFL framework (ccQFL) eliminating single-point-of-failure vulnerabilities and communication bottlenecks in distributed quantum ML.