CLAIR recovers the shared LoRA subspace and detects contaminated clients in heterogeneous federated settings through structured low-rank plus block-sparse decomposition, with theoretical recovery guarantees and empirical gains over local fine-tuning.
Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Federated LoRA Fine-Tuning for LLMs via Collaborative Alignment
CLAIR recovers the shared LoRA subspace and detects contaminated clients in heterogeneous federated settings through structured low-rank plus block-sparse decomposition, with theoretical recovery guarantees and empirical gains over local fine-tuning.