Divide and not forget: Ensemble of selectively trained experts in Continual Learning

By Grzegorz Rype's'c, Sebastian Cygert, Valeriya Khan, Tomasz Trzcinski, Bartosz Zieli'nski, Bartłomiej Twardowski. 2024

59 citations recorded by the source corpus.

Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixture-of-expert technique, where different models work together to solve the task. However, the experts are usually trained all at once using whole task data, which makes them all prone to forgetting and increasing computational burden. To address this limitation, we introduce a novel approach named SEED. SEED selects only one, the most optimal expert for a considered task, and uses data from this task to fine-tune only this expert. For this purpose, each expert represents each class with a Gaussian distribution, and the optimal expert is selected based on the similarity of those distributions. Consequently, SEED increases diversity and heterogeneity within the experts while maintaining the high stability of this ensemble method. The extensive experiments demonstrate that SEED achieves state-of-the-art performance in exemplar-free settings across various scenarios, showing the potential of expert diversification through data in continual learning.

Subfields: Artificial Intelligence

How researchers see this paper

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

In Artificial Intelligence

1. Jun Liu
2. Hossein Rahmani
3. Li Xu
4. Bryan M. Williams
5. Haoxuan Qu
6. G. Wang
7. Amir Shahroudy
8. Ajmal Saeed Mian

Citations in the corpus

• Recent Advances of Continual Learning in Computer Vision: An Overview (2021, positive): “For each following task, all the attention vectors calculated before are used as the masks to freeze the network parameters which are crucial for the previous tasks.”