2020
DOI: 10.48550/arxiv.2007.13904
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

La-MAML: Look-ahead Meta Learning for Continual Learning

Gunshi Gupta,
Karmesh Yadav,
Liam Paull

Abstract: The continual learning problem involves training models with limited capacity to perform well on a set of an unknown number of sequentially arriving tasks. While meta-learning shows great potential for reducing interference between old and new tasks, the current training procedures tend to be either slow or offline, and sensitive to many hyper-parameters. In this work, we propose Look-ahead MAML (La-MAML), a fast optimisation-based meta-learning algorithm for onlinecontinual learning, aided by a small episodic… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
34
0

Year Published

2021
2021
2022
2022

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 8 publications
(34 citation statements)
references
References 10 publications
0
34
0
Order By: Relevance
“…Intuitively, a basis will be regarded as important for preserving old knowledge if the gradients induced by new tasks and old ones are aligned in the opposite direction on that basis. As demonstrated through extensive experiments, our proposed method can consistently outperform the state-of-the-art methods [17,30,24,31,5,13,34] by a notable margin across a range of widely used benchmark datasets.…”
Section: Introductionmentioning
confidence: 81%
See 3 more Smart Citations
“…Intuitively, a basis will be regarded as important for preserving old knowledge if the gradients induced by new tasks and old ones are aligned in the opposite direction on that basis. As demonstrated through extensive experiments, our proposed method can consistently outperform the state-of-the-art methods [17,30,24,31,5,13,34] by a notable margin across a range of widely used benchmark datasets.…”
Section: Introductionmentioning
confidence: 81%
“…A few other works have utilized gradient information to protect previous knowledge. [31,13] adopt optimization-based meta-learning to enforce gradient alignment between samples from different tasks. GPM [34] minimizes interference between sequential tasks by ensuring that gradient updates only occur in directions orthogonal to the input of previous tasks.…”
Section: Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…In addition to OML, MAML [66] and its variant FOMAML [66] have been utilized. For example, Gupta et al [68] optimize the OML objective in an online way through a multistep MAML procedure. The authors indicate that the gradient alignment among old tasks does not degrade while a new task is learned in OML; therefore, it is necessary to avoid repeated optimization of the inter-task alignment between old tasks to enable acceleration.…”
Section: B Information Prospectionmentioning
confidence: 99%