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

TL;DR

Avalanche is an open-source library built on PyTorch that facilitates research, prototyping, and evaluation of continual learning algorithms in a reproducible and collaborative manner.

Contribution

It introduces Avalanche, a comprehensive library that simplifies implementation, evaluation, and sharing of continual learning methods for the deep learning community.

Findings

Enables reproducible benchmarking of continual learning algorithms.

Supports rapid prototyping and evaluation workflows.

Fosters collaborative research in continual learning.

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.