Memory Efficient Meta-Learning with Large Images

By Meta-Train, Meta-Test. 2021

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Zhenyi Wang
2. Richard E. Turner
3. Sebastian Nowozin
4. John F. Bronskill
5. Yoshua Bengio
6. Li Shen
7. Massimiliano Patacchiola
8. Aliaksandra Shysheya

Citations in the corpus

• FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification (2022, methodology): “Personalization requires models that can be updated inexpensively by minimizing the number of parameters that need to be stored and / or transmitted and frequently calls for few-shot learning methods as the amount of training data from an individual user may be small (Massiceti et al., 2021).”
• Meta-learning without data via Wasserstein distributionally-robust model fusion (2022, background): “…Rajeswaran et al., 2019, Finn et al., 2019b, Raghu et al., 2020, Wang et al., 2020b, Zhou et al., 2021, Bohdal et al., 2021, Rothfuss et al., 2021, CHEN et al., 2021, Bronskill et al., 2021, Sun et al., 2021] focus on the offline setting, where all the training tasks are available together upfront.”