SequeL: A Continual Learning Library in PyTorch and JAX
This is an incremental contribution that addresses reproducibility and progress issues for researchers and practitioners in continual learning.
The authors tackled the problem of divergent codebases in continual learning due to the rising popularity of JAX alongside PyTorch, by introducing SequeL, a flexible library that supports both frameworks and provides a unified interface for various algorithms.
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.