11 datasets found

The dataset used in the paper is a collection of meta-learning frameworks, including MAML, Prototypical Network, and others.

The Alchemy benchmark is a meta-learning environment rich enough to contain interesting abstractions, yet simple enough to make ne-grained analysis tractable.

The dataset used in the paper is a collection of environments with multiple confounders, including mass, length, damping, and a crippled leg. The dataset is used to evaluate the...

Opt-IML: Scaling language model instruction meta learning through the lens of generalization.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the Mini-Imagenet and CIFAR-FS datasets for few-shot learning tasks.

A new approach to meta-learning, called meta-meta classification, to learning in small-data settings.

RotoGBML: Towards out-of-distribution generalization for gradient-based meta-learning.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used various tasks such as Associative Retrieval Task, Maze Exploration, Atari...

The nf2vec dataset is used for training the meta-encoder of LLaNA.

A dataset of datasets for learning to learn from few examples.

This dataset is used to evaluate the performance of the proposed Meta-GraphSHS model for discovering structural hole spanners in diverse networks.