SequeL: A Continual Learning Library in PyTorch and JAX
- URL: http://arxiv.org/abs/2304.10857v1
- Date: Fri, 21 Apr 2023 10:00:22 GMT
- Title: SequeL: A Continual Learning Library in PyTorch and JAX
- Authors: Nikolaos Dimitriadis, Francois Fleuret, Pascal Frossard
- Abstract summary: SequeL is a library for Continual Learning that supports both PyTorch and JAX frameworks.
It provides a unified interface for a wide range of Continual Learning algorithms, including regularization-based approaches, replay-based approaches, and hybrid approaches.
We release SequeL as an open-source library, enabling researchers and developers to easily experiment and extend the library for their own purposes.
- Score: 50.33956216274694
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- VersiCode: Towards Version-controllable Code Generation [58.82709231906735]
Large Language Models (LLMs) have made tremendous strides in code generation, but existing research fails to account for the dynamic nature of software development.
We propose two novel tasks aimed at bridging this gap: version-specific code completion (VSCC) and version-aware code migration (VACM)
We conduct an extensive evaluation on VersiCode, which reveals that version-controllable code generation is indeed a significant challenge.
arXiv Detail & Related papers (2024-06-11T16:15:06Z) - Lightweight Syntactic API Usage Analysis with UCov [0.0]
We present a novel conceptual framework designed to assist library maintainers in understanding the interactions allowed by their APIs.
These customizable models enable library maintainers to improve their design ahead of release, reducing friction during evolution.
We implement these models for Java libraries in a new tool UCov and demonstrate its capabilities on three libraries exhibiting diverse styles of interaction.
arXiv Detail & Related papers (2024-02-19T10:33:41Z) - Avalanche: A PyTorch Library for Deep Continual Learning [12.238684710313168]
Continual learning is the problem of learning from a nonstationary stream of data.
Avalanche is an open source library maintained by the ContinualAI non-profit organization.
arXiv Detail & Related papers (2023-02-02T10:45:20Z) - MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning
Library [82.77446613763809]
We present MARLlib, a library designed to offer fast development for multi-agent tasks and algorithm combinations.
MARLlib can effectively disentangle the intertwined nature of the multi-agent task and the learning process of the algorithm.
The library's source code is publicly accessible on GitHub.
arXiv Detail & Related papers (2022-10-11T03:11:12Z) - PyRelationAL: A Library for Active Learning Research and Development [0.11545092788508224]
PyRelationAL is an open source library for active learning (AL) research.
It provides access to benchmark datasets and AL task configurations based on existing literature.
We perform experiments on the PyRelationAL collection of benchmark datasets and showcase the considerable economies that AL can provide.
arXiv Detail & Related papers (2022-05-23T08:21:21Z) - Latte: Cross-framework Python Package for Evaluation of Latent-Based
Generative Models [65.51757376525798]
Latte is a Python library for evaluation of latent-based generative models.
Latte is compatible with both PyTorch and/Keras, and provides both functional and modular APIs.
arXiv Detail & Related papers (2021-12-20T16:00:28Z) - Solo-learn: A Library of Self-supervised Methods for Visual
Representation Learning [83.02597612195966]
solo-learn is a library of self-supervised methods for visual representation learning.
Implemented in Python, using Pytorch and Pytorch lightning, the library fits both research and industry needs.
arXiv Detail & Related papers (2021-08-03T22:19:55Z) - MBRL-Lib: A Modular Library for Model-based Reinforcement Learning [13.467075854633213]
We present MBRL-Lib -- a machine learning library for model-based reinforcement learning in continuous state-action spaces based on PyTorch.
It is designed as a platform for both researchers, to easily develop, debug and compare new algorithms, and non-expert user, to lower the entry-bar of deploying state-of-the-art algorithms.
arXiv Detail & Related papers (2021-04-20T17:58:22Z) - Avalanche: an End-to-End Library for Continual Learning [81.84325803942811]
We propose Avalanche, an open-source library for continual learning research based on PyTorch.
Avalanche is designed to provide a shared and collaborative for fast prototyping, training, and reproducible evaluation of continual learning algorithms.
arXiv Detail & Related papers (2021-04-01T11:31:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.