Fed-TaLoRA uses task-agnostic low-rank residual adaptation with post-aggregation calibration to enable efficient federated continual fine-tuning across sequential tasks under non-IID conditions.
Continual adaptation of vision transformers for federated learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A survey organizing knowledge distillation techniques for addressing privacy, heterogeneity, communication, and personalization challenges in federated learning.
citing papers explorer
-
Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning
Fed-TaLoRA uses task-agnostic low-rank residual adaptation with post-aggregation calibration to enable efficient federated continual fine-tuning across sequential tasks under non-IID conditions.
-
Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions
A survey organizing knowledge distillation techniques for addressing privacy, heterogeneity, communication, and personalization challenges in federated learning.