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…
Modular Embedding Recomposition for Incremental Learning
Aniello Panariello, Emanuele Frascaroli, Pietro Buzzega +3
The advent of pre-trained Vision-Language Models (VLMs) has significantly transformed Continual Learning (CL), mainly due to their zero-shot classification abilities. Such proficie…
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…
Federated Class-Incremental Learning with Hierarchical Generative Prototypes
Riccardo Salami, Pietro Buzzega, Matteo Mosconi +2
Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy. On top of tha…
Closed-form merging of parameter-efficient modules for Federated Continual Learning
Riccardo Salami, Pietro Buzzega, Matteo Mosconi +3
Model merging has emerged as a crucial technique in Deep Learning, enabling the integration of multiple models into a unified system while preserving perfor-mance and scalability.…