Lee, S;
Mannelli, SS;
Clopath, C;
Goldt, S;
Saxe, AM;
(2022)
Maslow’s Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation.
In:
Proceedings of the 39th International Conference on Machine Learning, PMLR.
Proceedings of Machine Learning Research (PMLR)
Preview |
Text
lee22g.pdf - Published Version Download (19MB) | Preview |
Abstract
Continual learning—learning new tasks in sequence while maintaining performance on old tasks—remains particularly challenging for artificial neural networks. Surprisingly, the amount of forgetting does not increase with the dissimilarity between the learned tasks, but appears to be worst in an intermediate similarity regime. In this paper we theoretically analyse both a synthetic teacher-student framework and a real data setup to provide an explanation of this phenomenon that we name Maslow’s Hammer hypothesis. Our analysis reveals the presence of a trade-off between node activation and node re-use that results in worst forgetting in the intermediate regime. Using this understanding we reinterpret popular algorithmic interventions for catastrophic interference in terms of this trade-off, and identify the regimes in which they are most effective.
| Type: | Proceedings paper |
|---|---|
| Title: | Maslow’s Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation |
| Event: | ICML 2022 |
| Dates: | 17 Jul 2022 - 23 Jul 2022 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://proceedings.mlr.press/v162/lee22g.html |
| Language: | English |
| Additional information: | This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third-party material in this article are included in the Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neurosci Unit |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10160773 |
Archive Staff Only
 |
View Item |
