Avalanche: A PyTorch Library for Deep Continual Learning

02/02/2023
by   Antonio Carta, et al.
University of Bologna
Scuola Normale Superiore
University of Pisa
University of St. Gallen
0

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>.

READ FULL TEXT

page 2

page 4

04/24/2023

Renate: A Library for Real-World Continual Learning

Continual learning enables the incremental training of machine learning ...
04/18/2022

DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning

Coreset selection, which aims to select a subset of the most informative...
06/04/2021

A Procedural World Generation Framework for Systematic Evaluation of Continual Learning

Several families of continual learning techniques have been proposed to ...
06/10/2020

Dataset Condensation with Gradient Matching

Efficient training of deep neural networks is an increasingly important ...
04/20/2023

Robust Deep Reinforcement Learning Scheduling via Weight Anchoring

Questions remain on the robustness of data-driven learning methods when ...
10/01/2021

TyXe: Pyro-based Bayesian neural nets for Pytorch

We introduce TyXe, a Bayesian neural network library built on top of Pyt...
03/19/2023

SIESTA: Efficient Online Continual Learning with Sleep

In supervised continual learning, a deep neural network (DNN) is updated...

Please sign up or login with your details

Forgot password? Click here to reset