← Search

Mahdi Beitollahi

2 accepted papers

2026

Toward Enhancing Representation Learning in Federated Multi-Task Settings

ICLR 2026poster

Federated multi-task learning (FMTL) seeks to collaboratively train customized models for users with different tasks while preserving data privacy. Most existing approaches assume model congruity (i.e., the use of fully or partially homogeneous models) across users, which limits their applicability…

Cited by 0SourceScholar
2025

NoT: Federated Unlearning via Weight Negation

CVPR 2025poster

Federated unlearning (FU) aims to remove a participant's data contributions from a trained federated learning (FL) model, ensuring privacy and regulatory compliance. Traditional FU methods often depend on auxiliary storage on either the client or server side or require direct access to the data targ…

Cited by 1SourcePDFScholar