Leonardo Esteves
Papers
1
Total Citations
7
H-Index
1
About
Leonardo Esteves is a leading researcher in the rapidly evolving field of mobile and distributed machine learning, with a primary focus on **federated learning** and **edge intelligence**. His work tackles the critical challenge of training robust AI models across unreliable, heterogeneous networks of mobile devices. Esteves’s most notable contribution is his pioneering research on **selective aggregation** techniques, which enable federated learning systems to function effectively even when participants are intermittent or untrustworthy. His 2023 paper, "Towards Mobile Federated Learning with Unreliable Participants and Selective Aggregation," has already garnered 7 citations, signaling its growing influence in addressing real-world deployment hurdles. By developing algorithms that intelligently filter and weight contributions from unreliable nodes, Esteves is helping to unlock the potential of privacy-preserving AI in sensitive domains like healthcare and autonomous systems. His work directly confronts the tension between data utility and device autonomy, offering practical solutions for scaling AI without centralizing sensitive information. As federated learning moves from theory to practice, Esteves’s research provides the foundational robustness needed for dependable, decentralized intelligence.
Research Focus
Key Achievements
Top Papers
- 1