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 interest in continual learning, especially within the deep learning community. However, algorithmic solutions are often difficult to re-implement, evaluate and port across different settings, where even results on standard benchmarks are hard to reproduce. In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch. Avalanche is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms.

Vincenzo Lomonaco, L.P. (2021). Avalanche: an End-to-End Library for Continual Learning [10.1109/CVPRW53098.2021.00399].

Avalanche: an End-to-End Library for Continual Learning

Vincenzo Lomonaco
;
Lorenzo Pellegrini
;
Gabriele Graffieti
;
Davide Maltoni
2021

Abstract

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 interest in continual learning, especially within the deep learning community. However, algorithmic solutions are often difficult to re-implement, evaluate and port across different settings, where even results on standard benchmarks are hard to reproduce. In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch. Avalanche is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms.
2021
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2021)
3595
3605
Vincenzo Lomonaco, L.P. (2021). Avalanche: an End-to-End Library for Continual Learning [10.1109/CVPRW53098.2021.00399].
Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu, Antonio Carta, Gabriele Graffieti, Tyler L. Hayes, Matthias De Lange, Marc Masana, Jary Pomponi, ...espandi
File in questo prodotto:
File Dimensione Formato  
Lomonaco_Avalanche_An_End-to-End_Library_for_Continual_Learning_CVPRW_2021_paper.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 1.31 MB
Formato Adobe PDF
1.31 MB 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/11585/834411
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 90
  • ???jsp.display-item.citation.isi??? 45
social impact