Search Results for author:
Found 6 papers, 5 papers with code
Towards Cross-Domain Continual Learning
In this work, we introduce a novel approach called Cross-Domain Continual Learning (CDCL) that addresses the limitations of being limited to single supervised domains.
Class-Incremental Learning via Knowledge Amalgamation
Catastrophic forgetting has been a significant problem hindering the deployment of deep learning algorithms in the continual learning setting.
Reinforced Continual Learning for Graphs
Continual learning on graphs is largely unexplored and existing graph continual learning approaches are limited to the task-incremental learning scenarios.
Autonomous Cross Domain Adaptation under Extreme Label Scarcity
This paper aims to attack the problem of extreme label shortage in the cross domain multistream classification problems where only very few labelled samples of the source stream are provided before process runs.
ACDC: Online Unsupervised Cross-Domain Adaptation
We consider the problem of online unsupervised cross-domain adaptation, where two independent but related data streams with different feature spaces -- a fully labeled source stream and an unlabeled target stream -- are learned together.
ATL: Autonomous Knowledge Transfer from Many Streaming Processes
It automatically evolves its network structure from scratch with/without the presence of ground truth to overcome independent concept drifts in the source and target domain.
