learn2learn: A Library for Meta-Learning Research
Meta-learning researchers face two fundamental issues in their empirical work: prototyping and reproducibility. Researchers are prone to make mistakes when prototyping new algorithms and tasks because modern meta-learning methods rely on unconventional functionalities of machine learning frameworks. In turn, reproducing existing results becomes a tedious endeavour -- a situation exacerbated by the lack of standardized implementations and benchmarks. As a result, researchers spend inordinate amounts of time on implementing software rather than understanding and developing new ideas. This manuscript introduces learn2learn, a library for meta-learning research focused on solving those prototyping and reproducibility issues. learn2learn provides low-level routines common across a wide-range of meta-learning techniques (e.g. meta-descent, meta-reinforcement learning, few-shot learning), and builds standardized interfaces to algorithms and benchmarks on top of them. In releasing learn2learn under a free and open source license, we hope to foster a community around standardized software for meta-learning research.
Code (2)
Tasks
Few-Shot LearningMeta-LearningMeta Reinforcement LearningSimilar Papers 제목 키워드 기반
Torchmeta: A Meta-Learning library for PyTorch
The constant introduction of standardized benchmarks in the literature has helped accelerating the recent advances in meta-learning research. They offer a way to get a fair comparison between different algorithms, and th…
Meta-LearningUser Manual of Automatic Data Curation Tool(ADCT): A bulk data curator software in Library and Information Science
In library and information science, document storage and user-specific document retrieval are the main aspects of digital library services. To preserve the cultural heritage, documents, and literature, we need a common p…
DescriptiveRetrievalGeneralized Inner Loop Meta-Learning
Many (but not all) approaches self-qualifying as "meta-learning" in deep learning and reinforcement learning fit a common pattern of approximating the solution to a nested optimization problem. In this paper, we give a f…
Meta-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)DatAasee -- A Metadata-Lake as Metadata Catalog for a Virtual Data-Lake
Metadata management for distributed data sources is a long-standing but ever-growing problem. To counter this challenge in a research-data and library-oriented setting, this work constructs a data architecture, derived f…
ManagementBOML: A Modularized Bilevel Optimization Library in Python for Meta Learning
Meta-learning (a.k.a. learning to learn) has recently emerged as a promising paradigm for a variety of applications. There are now many meta-learning methods, each focusing on different modeling aspects of base and meta …
Bilevel OptimizationMeta-Learning