125 citations · 221 across the 28 of their papers we have counts for
27 papers · 1 filter
How to Find and Reuse Policies for Continuous Adaptation in Lifelong Reinforcement Learning
Saptarshi Nath, Inish M. D'Souza, Antonio Carta +2
In lifelong reinforcement learning, retaining previously learned policies is not sufficient for effective transfer to a new task. Useful knowledge may be distributed across several…
Z-PEFT: Zero-shot Backdoor Detection in Parameter-Efficient Fine-Tuning via Canonical Spectral Signatures
Nicola Pitzalis, Donald Shenaj, Giacomo Cignoni +3
Parameter-Efficient Fine-tuned (PEFT) models are frequently downloaded from open repositories by practitioners. This widespread practice creates a significant attack surface, as ma…
Position: Modular Memory is the Key to Continual Learning Agents
Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov +21
Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these…
CLA: Latent Alignment for Online Continual Self-Supervised Learning
Giacomo Cignoni, Andrea Cossu, Alexandra Gomez-Villa +2
Self-supervised learning (SSL) is able to build latent representations that generalize well to unseen data. However, only a few SSL techniques exist for the online CL setting, wher…
Continual Learning Should Move Beyond Incremental Classification
Rupert Mitchell, Antonio Alliegro, Raffaello Camoriano +17
Continual learning (CL) is the sub-field of machine learning concerned with accumulating knowledge in dynamic environments. So far, CL research has mainly focused on incremental cl…
Replay-free Online Continual Learning with Self-Supervised MultiPatches
Giacomo Cignoni, Andrea Cossu, Alex Gomez-Villa +2
Online Continual Learning (OCL) methods train a model on a non-stationary data stream where only a few examples are available at a time, often leveraging replay strategies. However…
A Comprehensive Empirical Evaluation on Online Continual Learning
Albin Soutif--Cormerais, Antonio Carta, Andrea Cossu +4
Online continual learning aims to get closer to a live learning experience by learning directly on a stream of data with temporally shifting distribution and by storing a minimum a…
Improving Online Continual Learning Performance and Stability with Temporal Ensembles
Albin Soutif--Cormerais, Antonio Carta, Joost Van de Weijer
Neural networks are very effective when trained on large datasets for a large number of iterations. However, when they are trained on non-stationary streams of data and in an onlin…
Projected Latent Distillation for Data-Agnostic Consolidation in Distributed Continual Learning
Antonio Carta, Andrea Cossu, Vincenzo Lomonaco +2
Distributed learning on the edge often comprises self-centered devices (SCD) which learn local tasks independently and are unwilling to contribute to the performance of other SDCs.…
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…
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…
Sample Condensation in Online Continual Learning
Mattia Sangermano, Antonio Carta, Andrea Cossu +1
Online Continual learning is a challenging learning scenario where the model must learn from a non-stationary stream of data where each sample is seen only once. The main challenge…
Continual Pre-Training Mitigates Forgetting in Language and Vision
Andrea Cossu, Tinne Tuytelaars, Antonio Carta +3
Pre-trained models are nowadays a fundamental component of machine learning research. In continual learning, they are commonly used to initialize the model before training on the s…
Avalanche RL: a Continual Reinforcement Learning Library
Nicolò Lucchesi, Antonio Carta, Vincenzo Lomonaco +1
Continual Reinforcement Learning (CRL) is a challenging setting where an agent learns to interact with an environment that is constantly changing over time (the stream of experienc…
Practical Recommendations for Replay-based Continual Learning Methods
Gabriele Merlin, Vincenzo Lomonaco, Andrea Cossu +2
Continual Learning requires the model to learn from a stream of dynamic, non-stationary data without forgetting previous knowledge. Several approaches have been developed in the li…
Ex-Model: Continual Learning from a Stream of Trained Models
Antonio Carta, Andrea Cossu, Vincenzo Lomonaco +1
Learning continually from non-stationary data streams is a challenging research topic of growing popularity in the last few years. Being able to learn, adapt, and generalize contin…
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 with Echo State Networks
Andrea Cossu, Davide Bacciu, Antonio Carta +2
Continual Learning (CL) refers to a learning setup where data is non stationary and the model has to learn without forgetting existing knowledge. The study of CL for sequential pat…
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…
Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification
Antonio Carta, Andrea Cossu, Federico Errica +1
In this work, we study the phenomenon of catastrophic forgetting in the graph representation learning scenario. The primary objective of the analysis is to understand whether class…
Distilled Replay: Overcoming Forgetting through Synthetic Samples
Andrea Rosasco, Antonio Carta, Andrea Cossu +2
Replay strategies are Continual Learning techniques which mitigate catastrophic forgetting by keeping a buffer of patterns from previous experiences, which are interleaved with new…
Continual Learning for Recurrent Neural Networks: an Empirical Evaluation
Andrea Cossu, Antonio Carta, Vincenzo Lomonaco +1
Learning continuously during all model lifetime is fundamental to deploy machine learning solutions robust to drifts in the data distribution. Advances in Continual Learning (CL) w…
Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization
Antonio Carta, Alessandro Sperduti, Davide Bacciu
Training RNNs to learn long-term dependencies is difficult due to vanishing gradients. We explore an alternative solution based on explicit memorization using linear autoencoders f…
Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic Memory
Antonio Carta, Alessandro Sperduti, Davide Bacciu
The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at differe…