A new probing framework detects moderate parametric memorization signals in tabular in-context learning models under single-task fine-tuning, strongest on low-cardinality tasks, but signals largely disappear under realistic training.
Selec- tive aggregation for low-rank adaptation in federated learning.arXiv preprint arXiv:2410.01463
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.LG 5verdicts
UNVERDICTED 5representative citing papers
FedRouter clusters adapters locally per task samples and globally across clients to create task-centric personalized models, improving generalization and reducing task interference in federated fine-tuning.
LA-LoRA decouples LoRA matrix updates in DPFL settings to improve robustness to privacy noise, delivering up to 16.83% higher accuracy than prior LoRA variants on Swin-B under strict epsilon=1.
Fed-DLoRA combines low-rank adaptation with federated learning and an adaptive rank-bandwidth-vehicle selection algorithm to improve accuracy, convergence speed, and communication efficiency in wireless IoV environments.
FediLoRA is a lightweight federated LoRA aggregation method that jointly mitigates missing modalities and heterogeneous ranks in collaborative fine-tuning of foundation models.
citing papers explorer
-
Probing Memorization of Tabular In-Context Learning
A new probing framework detects moderate parametric memorization signals in tabular in-context learning models under single-task fine-tuning, strongest on low-cardinality tasks, but signals largely disappear under realistic training.
-
Task-Centric Personalized Federated Fine-Tuning of Language Models
FedRouter clusters adapters locally per task samples and globally across clients to create task-centric personalized models, improving generalization and reducing task interference in federated fine-tuning.
-
Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models
LA-LoRA decouples LoRA matrix updates in DPFL settings to improve robustness to privacy noise, delivering up to 16.83% higher accuracy than prior LoRA variants on Swin-B under strict epsilon=1.
-
Fed-DLoRA: Efficient Wireless Federated Learning with Dynamic Low-Rank Adaptation
Fed-DLoRA combines low-rank adaptation with federated learning and an adaptive rank-bandwidth-vehicle selection algorithm to improve accuracy, convergence speed, and communication efficiency in wireless IoV environments.
-
FediLoRA: Practical Federated Fine-Tuning of Foundation Models Under Missing-Modality Constraints
FediLoRA is a lightweight federated LoRA aggregation method that jointly mitigates missing modalities and heterogeneous ranks in collaborative fine-tuning of foundation models.