Publications by Omayma Moussadek

Explore our research publications: papers, articles, and conference proceedings from AImageLab.

Tip: type @ to pick an author and # to pick a keyword.

Active filters (Clear): Author: Omayma Moussadek

DOLFIN: Balancing Stability and Plasticity in Federated Continual Learning

Authors: Moussadek, Omayma; Salami, Riccardo; Calderara, Simone

Published in: LECTURE NOTES IN COMPUTER SCIENCE

Federated continual learning (FCL) enables models to learn new tasks across multiple distributed clients, protecting privacy and without forgetting previously … (Read full abstract)

Federated continual learning (FCL) enables models to learn new tasks across multiple distributed clients, protecting privacy and without forgetting previously acquired knowledge. However, current methods face challenges balancing performance, privacy preservation, and communication efficiency. We introduce a Distributed Online LoRA for Federated INcremental learning methodDOLFIN, a novel approach combining Vision Transformers with low-rank adapters designed to efficiently and stably learn new tasks in federated environments. Our method leverages LoRA for minimal communication overhead and incorporates Dual Gradient Projection Memory (DualGPM) to prevent forgetting. Evaluated on CIFAR-100, ImageNet-R, ImageNet-A, and CUB-200 under two Dirichlet heterogeneity settings,DOLFINconsistently surpasses six strong baselines in final average accuracy while matching their memory footprint. Orthogonal low-rank adapters offer an effective and scalable solution for privacy-preserving continual learning in federated settings.

2026 Relazione in Atti di Convegno