VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty
By Randy Ardywibowo, Zepeng Huo, Zhangyang Wang, Bobak J. Mortazavi, Shuai Huang, Xiaoning Qian. 2022
11 citations recorded by the source corpus.
Subfields: Meta & Continual Learning, Neural Architecture Search & AutoML
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
- Xingxing Zhang
- Liyuan Wang
- Hang Su
- Jun Zhu
- Simone Scardapane
- Valerio Marsocci
- Liyuan Wang
- Hongwei Yan
Citations in the corpus
- A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, methodology): “VariGrow[270] employs an energy-based novelty score to decide whether to extend a new expert or update an old one.”
- Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization (2024, background): “Parameter-isolation-based approaches (Serra et al., 2018; Mallya & Lazebnik, 2018; Fernando et al., 2017; Aljundi et al., 2017; Ardywi-bowo et al., 2022; Wang et al., 2022) focus on isolating task-specific parameters to prevent interference between tasks.”