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. Unfortunately, deep learning libraries only provide primitives for offline training, assuming that model's architecture and data are fixed. Avalanche is an open source library maintained by the ContinualAI non-profit organization that extends PyTorch by providing first-class support for dynamic architectures, streams of datasets, and incremental training and evaluation methods. Avalanche provides a large set of predefined benchmarks and training algorithms and it is easy to extend and modular while supporting a wide range of continual learning scenarios. Documentation is available at https://avalanche.continualai.org.

Antonio Carta, L.P. (2023). Avalanche: A PyTorch Library for Deep Continual Learning. JOURNAL OF MACHINE LEARNING RESEARCH, 24, 1-6.

Avalanche: A PyTorch Library for Deep Continual Learning

Lorenzo Pellegrini;Vincenzo Lomonaco
2023

Abstract

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. Unfortunately, deep learning libraries only provide primitives for offline training, assuming that model's architecture and data are fixed. Avalanche is an open source library maintained by the ContinualAI non-profit organization that extends PyTorch by providing first-class support for dynamic architectures, streams of datasets, and incremental training and evaluation methods. Avalanche provides a large set of predefined benchmarks and training algorithms and it is easy to extend and modular while supporting a wide range of continual learning scenarios. Documentation is available at https://avalanche.continualai.org.
2023
Antonio Carta, L.P. (2023). Avalanche: A PyTorch Library for Deep Continual Learning. JOURNAL OF MACHINE LEARNING RESEARCH, 24, 1-6.
Antonio Carta, Lorenzo Pellegrini, Andrea Cossu, Hamed Hemati, Vincenzo Lomonaco
File in questo prodotto:
File Dimensione Formato  
23-0130.pdf

accesso aperto

Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 291.12 kB
Formato Adobe PDF
291.12 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/951104
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact