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.
Lomonaco, VincenzoPellegrini, LorenzoCossu, AndreaCarta, AntonioGraffieti, GabrieleHayes, Tyler L.De Lange, MatthiasMasana, MarcPomponi, Jaryvan de Ven, Gido M.Mundt, MartinShe, QiCooper, KeilandForest, JeremyBelouadah, EdenCalderara, Simone Parisi, German I.Cuzzolin, FabioTolias, Andreas S.Scardapane, SimoneAntiga, LucaAhmad, SubutaiPopescu, AdrianKanan, Christophervan de Weijer, JoostTuytelaars, TinneBacciu, DavideMaltoni, Davide
School of Engineering, Computing and Mathematics
Year of publication: 2021Date of RADAR deposit: 2021-10-25
“© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
RADAR: Research Archive and Digital Asset RepositoryAbout RADAR