Few-Shot Learning with Graph Neural Networks
ICLR(2017), cited over 600 times
![Untitled](https://s3-us-west-2.amazonaws.com/secure.notion-static.com/0ee35a5d-7907-448c-bba7-22ebd9849467/Untitled.png)
Summary
- Few shot learning을 위해 다른 sample과의 similarity 정보까지 이용(즉, 각 sample의 label을 독립적으로 학습하는데서 그치지 않음)
- 각 sample을 graph의 node라고 보고, edge는 두 sample간의 similarity kernel로 간주.
- Edge, 즉 similarity kernel은 trainable 함(즉, 단순한 inner product 등으로 pre-defined 되지 않음)
- Node의 feature는 message passing algorithm에서 착안하여 각 time step 마다 이웃 node에서 message를 받아서 업데이트됨.
- Semi-supervised learning, 더 나아가 active learning에도 적용 가능.
- Omniglot, Mini-ImageNet에 대해 더 적은 parameter로 state-of-the-art 성능을 보여줌(2017년 기준)
Keywords
- Few shot learning
- Graph neural network
- Semi-supervised learning
- Active learning with Attention
1. Introduction
- Supervised end-to-end learning has been extremely successful in computer vision, speech, or machine translation tasks.
- However, there are some tasks(e.g. few shot learning) that cannot achieve high performance with conventional methods.
- New supervised learning setup
- Input-output setup:
- With i.i.d. samples of collections of images and their associated label similarity
- cf) conventional setup: i.i.d. samples of images and their associated labels
- Authors' model can be extended to semi-supervised and active learning
-
Semi-supervised learning:
Learning from a mixture of labeled and unlabeled examples
![https://blog.est.ai/2020/11/ssl/](https://s3-us-west-2.amazonaws.com/secure.notion-static.com/ee1cb113-3f38-4c04-ae3f-d443a23414d3/Untitled.png)
https://blog.est.ai/2020/11/ssl/
-
Active learning:
The learner has the option to request those missing labels that will be most helpful for the prediction task
![ICML 2019 active learning tutorial](https://s3-us-west-2.amazonaws.com/secure.notion-static.com/eb342d8f-73f4-4cc0-8b7d-7563295673b2/Untitled.png)
ICML 2019 active learning tutorial
![Annotated by JH Gu](https://s3-us-west-2.amazonaws.com/secure.notion-static.com/4a982428-3432-47b8-bac5-f23edad18b2f/Untitled.png)
Annotated by JH Gu
2. Closely related works and ideas