Efficient Continual Learning Ensembles in Neural Network Subspaces

By Thang Van Doan, Seyed Iman Mirzadeh, Joelle Pineau, Mehrdad Farajtabar. 2022

7 citations recorded by the source corpus.

Subfields: Meta & Continual Learning

How researchers see this paper

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

In Meta & Continual Learning

1. Liyuan Wang
2. Xingxing Zhang
3. Jun Zhu
4. Hang Su
5. Yi Zhong
6. Qian Li
7. Thang Van Doan
8. Lucas Caccia

Citations in the corpus

• A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, methodology): “, using multiple continual learning models) [94], [353], [430].”
• CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One (2022, positive): “They further exploited recent advances of mode connectivity [30] and neural network subspace [48] to save computational cost, but had to use old training samples [13].”
• Building a Subspace of Policies for Scalable Continual Learning (2022, background): “[10] Thang Doan, Seyed Iman Mirzadeh, Joelle Pineau, and Mehrdad Farajtabar.”