12 citations · 30 across the 16 of their papers we have counts for
12 papers · 1 filter
C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift
Davide Domini, Gianluca Aguzzi, Lorenzo Pellegrini +2
Collective Adaptive Systems (CAS) increasingly rely on machine learning to let each node learn from locally sensed data, aligning its behavior with the surrounding environment. Sca…
Continual Learning in the Presence of Repetition
Hamed Hemati, Lorenzo Pellegrini, Xiaotian Duan +11
Continual learning (CL) provides a framework for training models in ever-evolving environments. Although re-occurrence of previously seen objects or tasks is common in real-world p…
Continual Learning by Three-Phase Consolidation
Davide Maltoni, Lorenzo Pellegrini
TPC (Three-Phase Consolidation) is here introduced as a simple but effective approach to continually learn new classes (and/or instances of known classes) while controlling forgett…
Avalanche: A PyTorch Library for Deep Continual Learning
Antonio Carta, Lorenzo Pellegrini, Andrea Cossu +2
Continual learning is the problem of learning from a nonstationary stream of data, a fundamental issue for sustainable and efficient training of deep neural networks over time. Unf…
Architect, Regularize and Replay (ARR): a Flexible Hybrid Approach for Continual Learning
Vincenzo Lomonaco, Lorenzo Pellegrini, Gabriele Graffieti +1
In recent years we have witnessed a renewed interest in machine learning methodologies, especially for deep representation learning, that could overcome basic i.i.d. assumptions an…
Class-Incremental Learning with Repetition
Hamed Hemati, Andrea Cossu, Antonio Carta +5
Real-world data streams naturally include the repetition of previous concepts. From a Continual Learning (CL) perspective, repetition is a property of the environment and, unlike r…
Generative Negative Replay for Continual Learning
Gabriele Graffieti, Davide Maltoni, Lorenzo Pellegrini +1
Learning continually is a key aspect of intelligence and a necessary ability to solve many real-life problems. One of the most effective strategies to control catastrophic forgetti…
Is Class-Incremental Enough for Continual Learning?
Andrea Cossu, Gabriele Graffieti, Lorenzo Pellegrini +4
The ability of a model to learn continually can be empirically assessed in different continual learning scenarios. Each scenario defines the constraints and the opportunities of th…
Continual Learning at the Edge: Real-Time Training on Smartphone Devices
Lorenzo Pellegrini, Vincenzo Lomonaco, Gabriele Graffieti +1
On-device training for personalized learning is a challenging research problem. Being able to quickly adapt deep prediction models at the edge is necessary to better suit personal…
Avalanche: an End-to-End Library for Continual Learning
Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu +25
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing…
Latent Replay for Real-Time Continual Learning
Lorenzo Pellegrini, Gabriele Graffieti, Vincenzo Lomonaco +1
Training deep neural networks at the edge on light computational devices, embedded systems and robotic platforms is nowadays very challenging. Continual learning techniques, where…
Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches
Vincenzo Lomonaco, Davide Maltoni, Lorenzo Pellegrini
Robotic vision is a field where continual learning can play a significant role. An embodied agent operating in a complex environment subject to frequent and unpredictable changes i…