6 papers
Toward Enhancing Representation Learning in Federated Multi-Task Settings
Mehdi Setayesh, Mahdi Beitollahi, Yasser H. Khalil +1
Federated multi-task learning (FMTL) seeks to collaboratively train customized models for users with different tasks while preserving data privacy. Most existing approaches assume…
Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising
Mateo Clemente, Leo Brunswic, Rui Heng Yang +5
Diffusion models, such as diffusion policy, have achieved state-of-the-art results in robotic manipulation by imitating expert demonstrations. While diffusion models were originall…
CoUn: Empowering Machine Unlearning via Contrastive Learning
Yasser H. Khalil, Mehdi Setayesh, Hongliang Li
Machine unlearning (MU) aims to remove the influence of specific "forget" data from a trained model while preserving its knowledge of the remaining "retain" data. Existing MU metho…
NoT: Federated Unlearning via Weight Negation
Yasser H. Khalil, Leo Brunswic, Soufiane Lamghari +3
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…
Does Combining Parameter-efficient Modules Improve Few-shot Transfer Accuracy?
Nader Asadi, Mahdi Beitollahi, Yasser Khalil +3
Parameter-efficient fine-tuning stands as the standard for efficiently fine-tuning large language and vision models on downstream tasks. Specifically, the efficiency of low-rank ad…
DFML: Decentralized Federated Mutual Learning
Yasser H. Khalil, Amir H. Estiri, Mahdi Beitollahi +5
In the realm of real-world devices, centralized servers in Federated Learning (FL) present challenges including communication bottlenecks and susceptibility to a single point of fa…