FedSAF shifts prototype alignment in heterogeneous federated learning from coordinate matching to inter-class structural relations and reports up to 3.52% gains over prior methods.
Character-level convolutional net- works for text classification
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
dataset 1polarities
use dataset 1representative citing papers
AdaLoc keeps a model locked to authorized users by confining all post-deployment updates to a chosen subset of weights, preserving both task performance for authorized use and near-random accuracy for unauthorized use across vision and language models.
GRMP crafts malicious updates via variational graph autoencoders on overheard benign feature graphs, degrading global LLM accuracy in federated IoA while evading statistical detection.
Graph representation learning plus iterative augmented Lagrangian optimization creates stronger, harder-to-detect model manipulation attacks on federated LLM fine-tuning, cutting global accuracy by up to 26%.
citing papers explorer
-
From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning
FedSAF shifts prototype alignment in heterogeneous federated learning from coordinate matching to inter-class structural relations and reports up to 3.52% gains over prior methods.
-
Re-Key-Free, Risky-Free: Adaptable Model Usage Control
AdaLoc keeps a model locked to authorized users by confining all post-deployment updates to a chosen subset of weights, preserving both task performance for authorized use and near-random accuracy for unauthorized use across vision and language models.
-
Graph Representation-based Model Poisoning on the Heterogeneous Internet of Agents
GRMP crafts malicious updates via variational graph autoencoders on overheard benign feature graphs, degrading global LLM accuracy in federated IoA while evading statistical detection.
-
Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs
Graph representation learning plus iterative augmented Lagrangian optimization creates stronger, harder-to-detect model manipulation attacks on federated LLM fine-tuning, cutting global accuracy by up to 26%.