Riccardo Salami
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Riccardo Salami has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Simone Calderara
University of Modena and Reggio Emilia
6 shared publications - Omayma Moussadek
University of Modena and Reggio Emilia
3 shared publications - Cosimo Fiorini
University of Modena and Reggio Emilia
2 shared publications - Daniela Gandolfi
University of Modena and Reggio Emilia
1 shared publication - Lorenzo Tartarini
University of Modena and Reggio Emilia
1 shared publication - Matteo Gianferrari
University of Modena and Reggio Emilia
1 shared publication
Latest Publications
- 3 August 2026
- Published by Springer Nature
- p. 385-400
STAER: Temporal Aligned Rehearsal for Continual Spiking Neural Network
- 3 August 2026
- Published by Springer Nature
- p. 385-400
STAER: Temporal Aligned Rehearsal for Continual Spiking Neural Network
- 13 January 2026
- Published by Springer Nature
- p. 202-210
Towards Robust Knowledge Removal in Federated Learning with High Data Heterogeneity
- 13 January 2026
- Published by Springer Nature
- p. 202-210
Towards Robust Knowledge Removal in Federated Learning with High Data Heterogeneity
- 13 January 2026
- Published by Springer Nature
- p. 175-183
DOLFIN: Balancing Stability and Plasticity in Federated Continual Learning
- 13 January 2026
- Published by Springer Nature
- p. 175-183
DOLFIN: Balancing Stability and Plasticity in Federated Continual Learning
- 2 January 2026
- Published by Springer Nature
- p. 128-142
Intrinsic Training Signals for Federated Learning Aggregation
- 2 January 2026
- Published by Springer Nature
- p. 128-142
Intrinsic Training Signals for Federated Learning Aggregation
- Open Access
Towards Robust Knowledge Removal in Federated Learning with High Data Heterogeneity
Nowdays, there are an abundance of portable devices capable of collecting large amounts of data and with decent computational power. This opened the possibility to train AI models in a distributed manner, preserving the participating clients' privacy. However, because of privacy regulations and safety requirements, elimination upon necessity of a client contribution to the model has become mandatory. The cleansing process must satisfy specific efficacy and time requirements. In recent years, research efforts have produced several knowledge removal methods, but these require multiple communication rounds between the data holders and the process coordinator. This can cause the unavailability of an effective model up to the end of the removal process, which can result in a disservice to the system users. In this paper, we introduce an innovative solution based on Task Arithmetic and the Neural Tangent Kernel, to rapidly remove a client's influence from a model.
Open AccessTowards Robust Knowledge Removal in Federated Learning with High Data Heterogeneity
Nowdays, there are an abundance of portable devices capable of collecting large amounts of data and with decent computational power. This opened the possibility to train AI models in a distributed manner, preserving the participating clients' privacy. However, because of privacy regulations and safety requirements, elimination upon necessity of a client contribution to the model has become mandatory. The cleansing process must satisfy specific efficacy and time requirements. In recent years, research efforts have produced several knowledge removal methods, but these require multiple communication rounds between the data holders and the process coordinator. This can cause the unavailability of an effective model up to the end of the removal process, which can result in a disservice to the system users. In this paper, we introduce an innovative solution based on Task Arithmetic and the Neural Tangent Kernel, to rapidly remove a client's influence from a model.
- Open Access
DOLFIN: Balancing Stability and Plasticity in Federated Continual Learning
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 method DOLFIN, 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 DualGradient Projection Memory (DualGPM) to prevent forgetting. Evaluated on CIFAR-100, ImageNet-R, ImageNet-A, and CUB-200 under two Dirichlet heterogeneity settings, DOLFIN consistently 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.
Open AccessDOLFIN: Balancing Stability and Plasticity in Federated Continual Learning
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 method DOLFIN, 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 DualGradient Projection Memory (DualGPM) to prevent forgetting. Evaluated on CIFAR-100, ImageNet-R, ImageNet-A, and CUB-200 under two Dirichlet heterogeneity settings, DOLFIN consistently 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.