Papers
1
Total Citations
4
H-Index
1
About
Jaya Sharma is a rising researcher in the field of distributed machine learning and privacy-preserving systems, with a focused expertise in federated learning (FL) for Internet of Things (IoT) applications. Her most cited work, "HAFedL: A Hessian-Aware Adaptive Privacy Preserving Horizontal Federated Learning Scheme for IoT Applications" (2024), introduces a novel framework that enhances both communication efficiency and data security in FL environments. By incorporating Hessian-aware optimization and adaptive privacy mechanisms, Sharma addresses critical challenges in IoT networks—such as bandwidth constraints and vulnerability to adversarial attacks—while maintaining model accuracy. Although early in her career, this paper has already garnered 4 citations, signaling growing recognition of her contributions. Her work stands out for its dual focus on theoretical rigor and practical deployment, offering a scalable solution for real-world IoT systems. Sharma’s research is particularly impactful for students and engineers seeking to balance privacy, performance, and resource constraints in decentralized learning. As she continues to publish, her innovative approach to federated learning promises to shape the next generation of secure, efficient IoT architectures.
Research Focus
Key Achievements
Top Papers
- 1