paper-with-me

Papers

learn2learn: A Library for Meta-Learning Research

2020-08-27 · Sébastien M. R. Arnold, Praateek Mahajan, Debajyoti Datta, Ian Bunner, Konstantinos Saitas Zarkias

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.

📄 PDF Abstract BibTeX arXiv:2008.12284

Code (2)

learnables/learn2learn 공식 구현 pytorch
lukastrm/metakkl pytorch

Tasks

Few-Shot LearningMeta-LearningMeta Reinforcement Learning

Similar Papers 제목 키워드 기반

Torchmeta: A Meta-Learning library for PyTorch

2019-09-14 · Tristan Deleu, Tobias Würfl, Mandana Samiei, Joseph Paul Cohen 외

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-Learning

User Manual of Automatic Data Curation Tool(ADCT): A bulk data curator software in Library and Information Science

2022-10-31 · A. Banerjee, B. Sutradhar

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…

DescriptiveRetrieval

Generalized Inner Loop Meta-Learning

2019-10-03 · Edward Grefenstette, Brandon Amos, Denis Yarats, Phu Mon Htut 외

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

2024-09-09 · Christian Himpe

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…

Management

BOML: A Modularized Bilevel Optimization Library in Python for Meta Learning

2020-09-28 · Yaohua Liu, Risheng Liu

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