Sharing Knowledge for Meta-learning with Feature DescriptionsDownload PDF

Published: 31 Oct 2022, 18:00, Last Modified: 04 Jan 2023, 02:05NeurIPS 2022 AcceptReaders: Everyone
Keywords: Meta-learning, Few-shot learning
Abstract: Language is an important tool for humans to share knowledge. We propose a meta-learning method that shares knowledge across supervised learning tasks using feature descriptions written in natural language, which have not been used in the existing meta-learning methods. The proposed method improves the predictive performance on unseen tasks with a limited number of labeled data by meta-learning from various tasks. With the feature descriptions, we can find relationships across tasks even when their feature spaces are different. The feature descriptions are encoded using a language model pretrained with a large corpus, which enables us to incorporate human knowledge stored in the corpus into meta-learning. In our experiments, we demonstrate that the proposed method achieves better predictive performance than the existing meta-learning methods using a wide variety of real-world datasets provided by the statistical office of the EU and Japan.
Supplementary Material: pdf
10 Replies