Integrating Curricula with Replays: Its Effects on Continual Learning

Page view(s)
18
Checked on Jan 11, 2025
Integrating Curricula with Replays: Its Effects on Continual Learning
Title:
Integrating Curricula with Replays: Its Effects on Continual Learning
Journal Title:
The AAAI Conference on Artificial Intelligence (AAAI), summer symposium
Publication Date:
17 July 2023
Citation:
Tee, R.J. and Zhang, M., 2023, October. Integrating Curricula with Replays: Its Effects on Continual Learning. In Proceedings of the AAAI Symposium Series (Vol. 1, No. 1, pp. 109-116).
Abstract:
Humans engage in learning and reviewing processes with curricula when acquiring new skills or knowledge. This human learning behavior has inspired the integration of curricula with replay methods in continual learning agents. The goal is to emulate the human learning process, thereby improving knowledge retention and facilitating learning transfer. Existing replay methods in continual learning agents involve the random selection and ordering of data from previous tasks, which has shown to be effective. However, limited research has explored the integration of different curricula with replay methods to enhance continual learning. Our study takes initial steps in examining the impact of integrating curricula with replay methods on continual learning in three specific aspects: the interleaved frequency of replayed exemplars with training data, the sequence in which exemplars are replayed, and the strategy for selecting exemplars into the replay buffer. These aspects of curricula design align with cognitive psychology principles and leverage the benefits of interleaved practice during replays, easy-to-hard rehearsal, and exemplar selection strategy involving exemplars from a uniform distribution of difficulties. Based on our results, these three curricula effectively mitigated catastrophic forgetting and enhanced positive knowledge transfer, demonstrating the potential of curricula in advancing continual learning methodologies. Our code and data are available: https://github.com/ZhangLab- DeepNeuroCogLab/Integrating-Curricula-with-Replays
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation - AI Singapore
Grant Reference no. : AISG2-RP-2021-025

This research / project is supported by the National Research Foundation - NRF Fellowship
Grant Reference no. : NRF-NRFF15-2023-0001

This research / project is supported by the A*STAR - Early Career Investigatorship from Center for Frontier AI Research (CFAR),
Grant Reference no. : N.A

This research / project is supported by the A*STAR - Startup Grant
Grant Reference no. : N.A
Description:
NA
ISSN:

Files uploaded:

File Size Format Action
27486-article-text-31537-1-2-20231003.pdf 149.70 KB PDF Open