Context-Aware Meta-Learning
Christopher Fifty, Dennis Duan, Ronald Guenther Junkins, Ehsan Amid, Jure Leskovec, Christopher Re, Sebastian Thrun
Abstract
Large Language Models like ChatGPT demonstrate a remarkable capacity to learn new concepts during inference without any fine-tuning. However, visual models trained to detect new objects during inference have been unable to replicate this ability, and instead either perform poorly or require meta-training and/or fine-tuning on similar objects. In this work, we propose a meta-learning algorithm that emulates Large Language Models by learning new visual concepts during inference without fine-tuning. Our approach leverages a frozen pre-trained feature extractor, and analogous to in-context learning, recasts meta-learning as sequence modeling over datapoints with known labels and a test datapoint with an unknown label. On 8 out of 11 meta-learning benchmarks, our approach---without meta-training or fine-tuning---exceeds or matches the state-of-the-art algorithm, P>M>F, which is meta-trained on these benchmarks.
BibTeX
@inproceedings{
fifty2024contextaware,
title={Context-Aware Meta-Learning},
author={Christopher Fifty and Dennis Duan and Ronald Guenther Junkins and Ehsan Amid and Jure Leskovec and Christopher Re and Sebastian Thrun},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=lJYAkDVnRU}
}