Yap, Pauching;
Ritter, Hippolyt;
Barber, David;
(2021)
Addressing Catastrophic Forgetting in Few-Shot Problems.
In: Meila, M and Zhang, T, (eds.)
Proceedings of the 38th International Conference on Machine Learning.
(pp. pp. 1-11).
PMLR
Preview |
Text
yap21a.pdf - Published Version Download (3MB) | Preview |
Abstract
Neural networks are known to suffer from catastrophic forgetting when trained on sequential datasets. While there have been numerous attempts to solve this problem in large-scale supervised classification, little has been done to overcome catastrophic forgetting in few-shot classification problems. We demonstrate that the popular gradient-based model-agnostic meta-learning algorithm (MAML) indeed suffers from catastrophic forgetting and introduce a Bayesian online meta-learning framework that tackles this problem. Our framework utilises Bayesian online learning and meta-learning along with Laplace approximation and variational inference to overcome catastrophic forgetting in few-shot classification problems. The experimental evaluations demonstrate that our framework can effectively achieve this goal in comparison with various baselines. As an additional utility, we also demonstrate empirically that our framework is capable of meta-learning on sequentially arriving few-shot tasks from a stationary task distribution.
| Type: | Proceedings paper |
|---|---|
| Title: | Addressing Catastrophic Forgetting in Few-Shot Problems |
| Event: | Proceedings of the 38th International Conference on Machine Learning |
| Location: | Virtual |
| Dates: | 18th-24th July 2021 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://proceedings.mlr.press/v139/yap21a.html |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher's terms and conditions. |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10148253 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
