FedProTIP combines gradient projection onto orthogonal complements of prior-task subspaces with subspace-relevance task-identity prediction to achieve replay-free, task-agnostic federated continual learning.
We set the task identity prediction threshold toϵl = 0.95,∀l , based on a hyperparameter search
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection
FedProTIP combines gradient projection onto orthogonal complements of prior-task subspaces with subspace-relevance task-identity prediction to achieve replay-free, task-agnostic federated continual learning.