Continual Learning On Asc 19 Tasks

Metriken

F1 - macro

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

		Paper Title
Multi-task Learning (MTL; Upper Bound)	0.8811	Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning
CTR	0.8362	Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning
B-CL	0.8140	Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks
LAMOL	0.8059	LAMOL: LAnguage MOdeling for Lifelong Language Learning
OWM	0.7931	Continual Learning of Context-dependent Processing in Neural Networks
A-GEM	0.7844	Efficient Lifelong Learning with A-GEM
HAT	0.7816	Overcoming catastrophic forgetting with hard attention to the task
Independent Learning (ONE)	0.7807	Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning
KAN	0.7738	Continual Learning with Knowledge Transfer for Sentiment Classification
Naive Continual Learning (NCL)	0.7664	Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning
UCL	0.7599	Uncertainty-based Continual Learning with Adaptive Regularization
DER++	0.7508	Dark Experience for General Continual Learning: a Strong, Simple Baseline
EWC	0.7452	Overcoming catastrophic forgetting in neural networks
CAT	0.6864	Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks
L2	0.5243	Overcoming catastrophic forgetting in neural networks

0 of 15 row(s) selected.

Continual Learning On Asc 19 Tasks | SOTA | HyperAI