SequeL: A Continual Learning Library in PyTorch and JAX

TL;DR

SequeL is an open-source, flexible library supporting both PyTorch and JAX for continual learning, aiming to unify algorithms and improve reproducibility in the field.

Contribution

It introduces a modular, unified library for continual learning compatible with PyTorch and JAX, facilitating experimentation and extension.

Findings

Supports a wide range of continual learning algorithms

Enhances reproducibility across frameworks

Designed for ease of use and extensibility

Abstract

Continual Learning is an important and challenging problem in machine learning, where models must adapt to a continuous stream of new data without forgetting previously acquired knowledge. While existing frameworks are built on PyTorch, the rising popularity of JAX might lead to divergent codebases, ultimately hindering reproducibility and progress. To address this problem, we introduce SequeL, a flexible and extensible library for Continual Learning that supports both PyTorch and JAX frameworks. SequeL provides a unified interface for a wide range of Continual Learning algorithms, including regularization-based approaches, replay-based approaches, and hybrid approaches. The library is designed towards modularity and simplicity, making the API suitable for both researchers and practitioners. We release SequeL\footnote{\url{https://github.com/nik-dim/sequel}} as an open-source library, enabling researchers and developers to easily experiment and extend the library for their own purposes.