Meta Learning Python Packages

pyglove

Manipulating Python Programs

openml

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

torchmeta

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

paddlefsl

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

activations

AReLU: Attention-based-Rectified-Linear-Unit

torchopt

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

learn2learn

A PyTorch Library for Meta-learning Research

pymfe

Python Meta-Feature Extractor package.

pfnstudio

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

easyfsl

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

neuralprocesses

A framework for composing Neural Processes in Python

betty-ml

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

iltm

iLTM: Integrated Large Tabular Model

pfnstudio-core

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

tasksource

Preprocessings to prepare datasets for a task

dataset2vec

Implementation of the dataset2vec meta-feature extractor

deeppipe-api

[KDD 2023] Deep Pipeline Embeddings for AutoML

disco-torch

A PyTorch port of DeepMind's Disco103 — the meta-learned reinforcement learning update rule from Discovering State-of-the-art Reinforcement Learning Algorithms (Nature, 2025).

metadentify

Meta-/in-context/amortized causal inference for computational identifiability

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!

xenoverse

Benchmarking general decision-making with open & random worlds

redco

No description available

metavisionary

It empowers users to train machine learning models efficiently even when confronted with datasets containing a limited number of samples and classes that bear resemblance to each other.

simplemaml

A generic Python and TensorFlow function that implements a simple version of the "Model-Agnostic Meta-Learning (MAML) Algorithm for Fast Adaptation of Deep Networks" as designed by Chelsea Finn et al. 2017