Federated Continual Learning | Federated Fine-Tuning | Federated Representation Learning
I am a Ph.D. student in Computer Science at Iowa State University, working in the Software Analytics and Pervasive Parallelism Lab under the supervision of Ali Jannesari. My research builds federated and continual representation learning methods that let distributed models adapt across heterogeneous data and architectures, aligning knowledge representations to improve efficiency, privacy, and scalability.
I develop representation-level and parameter-efficient methods that fine-tune hidden representations and continually adapt large language models without sharing full models or overwriting prior knowledge. I focus on challenges such as semantic misalignment, domain shift, catastrophic forgetting, and communication constraints. I received my M.S. in Computer Science from Iowa State University, and earlier my M.S. and B.Sc. in Computer Science and Engineering from Jagannath University, Bangladesh.
I am currently a Ph.D. Intern at Pacific Northwest National Laboratory (PNNL), where I design Mixture-of-Experts foundation models for domain adaptation and generalization over distributed scientific data. See my Projects and Publications for more.
anwarcsejnu at gmail dot com