Meta Learning Python Packages

pyglove

Manipulating Python Programs

openml

OpenML's Python API for a World of Data and More 💫

torchopt

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

paddlefsl

FSL-Mate: A collection of resources for few-shot learning (FSL).

tasksource

Datasets collection and preprocessings framework for NLP extreme multitask learning

pymfe

Python Meta-Feature Extractor package.

neuralprocesses

A framework for composing Neural Processes in Python

fintfm

A tabular foundation model for corporate credit risk, pretrained only on synthetic data and measured in public, including where it loses.

learn2learn

A PyTorch Library for Meta-learning Research

iltm

iLTM: Integrated Large Tabular Model

rlschool

Collection of Reinforcement Learning / Meta Reinforcement Learning Environments.

torchmeta

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

easyfsl

Ready-to-use code and tutorial notebooks to boost your way into few-shot learning for image classification.

less-learn

Learning with Subset Stacking

redco

NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference

pfnstudio

Open-source toolkit + marketplace for prior-fitted foundation models (PFNs)

atomic-rl

Reinforcement learning utilities for Deep RL and the Alberta Plan: readable implementations of DQN, Rainbow, PPO, and MCTS.

cwru-plus

Ultra-fast, customizable CWRU dataset pipeline optimized for Deep Learning, Domain Adaptation, and parallel digital signal processing.

simplemaml

A simple generic (TensorFlow) function that implements the MAML algorithm for regression problems as designed by Chelsea Finn et al. 2017

xenoverse

Benchmarking general decision-making with open & random worlds

betty-ml

Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization

deeppipe-api

[KDD 2023] Deep Pipeline Embeddings for AutoML

pykale

Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for interdisciplinary research, part of the 🔥PyTorch ecosystem. ⭐ Star to support our work!

pfnstudio-core

Open-source toolkit + marketplace for prior-fitted foundation models (PFNs)