8 papers
Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
Angelo Porrello, Pietro Buzzega, Felix Dangel +4
Task Arithmetic yields a modular, scalable way to adapt foundation models. Combining multiple task vectors, however, can lead to cross-task interference, causing representation dri…
Rethinking Layer-wise Model Merging through Chain of Merges
Pietro Buzzega, Riccardo Salami, Angelo Porrello +1
Fine-tuning pretrained models has become a standard pathway to achieve state-of-the-art performance across a wide range of domains, leading to a proliferation of task-specific mode…
STAER: Temporal Aligned Rehearsal for Continual Spiking Neural Network
Matteo Gianferrari, Omayma Moussadek, Riccardo Salami +4
Spiking Neural Networks (SNNs) are inherently suited for continuous learning due to their event-driven temporal dynamics; however, their application to Class-Incremental Learning (…
Towards Robust Knowledge Removal in Federated Learning with High Data Heterogeneity
Riccardo Santi, Riccardo Salami, Simone Calderara
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…
DOLFIN: Balancing Stability and Plasticity in Federated Continual Learning
Omayma Moussadek, Riccardo Salami, Simone Calderara
Federated continual learning (FCL) enables models to learn new tasks across multiple distributed clients, protecting privacy and without forgetting previously acquired knowledge. H…
Intrinsic Training Signals for Federated Learning Aggregation
Cosimo Fiorini, Matteo Mosconi, Pietro Buzzega +2
Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy. While existing approaches for aggregating client-specific cla…