MetaFun: meta-learning with iterative functional updates

Conference item

We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one. Furthermore, rather than directly producing the representation, we learn a neural update rule resembling functional gradient descent which iteratively improves the representation. The final representation is used to condition the decoder to make predictions on unlabeled data. Our approach is the first to demonstrates the success of encoder-decoder style meta-learning methods like conditional neural processes on large-scale few-shot classification benchmarks such as miniImageNet and tieredImageNet, where it achieves state-of-the-art performance.

Authors: Xu, J; Ton, J-F; Kim, H; Kosiorek, AR; Teh, YW

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: PMLR
• Host title: Proceedings of the 37th International Conference on Machine Learning
• Pages: 10617-10627
• Series: Proceedings of Machine Learning Research
• Series number: 119
• Publication date: 2020-08-14
• Acceptance date: 2020-06-01
• Event title: 37th International Conference on Machine Learning
• Event location: Virtual event
• Event website: https://icml.cc/Conferences/2020
• Event start date: 2020-07-12
• Event end date: 2020-07-18
• ISSN: 2640-3498
• Language: English