# Torchmeta: A Meta-Learning library for PyTorch

arXiv: https://arxiv.org/abs/1909.06576 · HTML: https://mlsanity.com/paper/1909.06576/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2019.

## Built on by (most cited first, 30 of 52)

- [Offline Meta-Reinforcement Learning with Advantage Weighting](https://mlsanity.com/paper/2008.06043/) (2020)
- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [TorchGeo: Deep Learning With Geospatial Data](https://mlsanity.com/paper/2111.08872/) (2021)
- [FLEX: Unifying Evaluation for Few-Shot NLP](https://mlsanity.com/paper/2107.07170/) (2021)
- [Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning](https://mlsanity.com/paper/2206.03996/) (2022)
- [A Modern Self-Referential Weight Matrix That Learns to Modify Itself](https://mlsanity.com/paper/2202.05780/) (2022)
- [Learning where to learn: Gradient sparsity in meta and continual learning](https://mlsanity.com/paper/2110.14402/) (2021)
- [Betty: An Automatic Differentiation Library for Multilevel Optimization](https://mlsanity.com/paper/2207.02849/) (2022)
- [TorchOpt: An Efficient Library for Differentiable Optimization](https://mlsanity.com/paper/2211.06934/) (2022)
- [VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution](https://mlsanity.com/paper/2304.01434/) (2023)
- [Making Scalable Meta Learning Practical](https://mlsanity.com/paper/2310.05674/) (2023)
- [A contrastive rule for meta-learning](https://mlsanity.com/paper/2104.01677/) (2021)
- [A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning](https://mlsanity.com/paper/2106.15615/) (2021)
- [Meta-Learning with a Geometry-Adaptive Preconditioner](https://mlsanity.com/paper/2304.01552/) (2023)
- [The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence](https://mlsanity.com/paper/2208.01545/) (2022)
- [Meta-learning in healthcare: A survey](https://mlsanity.com/paper/2308.02877/) (2023)
- [Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers](https://mlsanity.com/paper/2405.15926/) (2024)
- [Minimax Optimization with Smooth Algorithmic Adversaries](https://mlsanity.com/paper/2106.01488/) (2021)
- [Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awareness](https://mlsanity.com/paper/2109.14120/) (2021)
- [On the Generalization and Adaption Performance of Causal Models](https://mlsanity.com/paper/2206.04620/) (2022)
- [p-Meta: Towards On-device Deep Model Adaptation](https://mlsanity.com/paper/2206.12705/) (2022)
- [Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes](https://mlsanity.com/paper/2301.06806/) (2023)
- [Metalearning Continual Learning Algorithms](https://mlsanity.com/paper/2312.00276/) (2023)
- [Differentiable Model Predictive Control on the GPU](https://mlsanity.com/paper/2510.06179/) (2025)
- [Is Pre-training Truly Better Than Meta-Learning?](https://mlsanity.com/paper/2306.13841/) (2023)
- [Graph Representation Learning for Multi-Task Settings: a Meta-Learning Approach](https://mlsanity.com/paper/2201.03326/) (2022)
- [Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks](https://mlsanity.com/paper/2205.15619/) (2022)
- [Frame Interpolation for Dynamic Scenes with Implicit Flow Encoding](https://mlsanity.com/paper/2209.13284/) (2022)
- [Adaptive Prototypical Networks](https://mlsanity.com/paper/2211.12479/) (2022)
- [Federated Conditional Stochastic Optimization](https://mlsanity.com/paper/2310.02524/) (2023)

## Abstract (arXiv)

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 the wide range of datasets available allows full control over the complexity of this evaluation. However, for a large majority of code available online, the data pipeline is often specific to one dataset, and testing on another dataset requires significant rework. We introduce Torchmeta, a library built on top of PyTorch that enables seamless and consistent evaluation of meta-learning algorithms on multiple datasets, by providing data-loaders for most of the standard benchmarks in few-shot classification and regression, with a new meta-dataset abstraction. It also features some extensions for PyTorch to simplify the development of models compatible with meta-learning algorithms. The code is available here: https://github.com/tristandeleu/pytorch-meta