Federated learning for generalization, robustness, fairness: A survey and benchmark
Federated learning has emerged as a promising paradigm for privacy-preserving
collaboration among different parties. Recently, with the popularity of federated learning, an …
collaboration among different parties. Recently, with the popularity of federated learning, an …
Fisher calibration for backdoor-robust heterogeneous federated learning
Federated learning presents massive potential for privacy-friendly vision task collaboration.
However, the federated visual performance is deeply affected by backdoor attacks, where …
However, the federated visual performance is deeply affected by backdoor attacks, where …
Vertical federated learning for effectiveness, security, applicability: A survey
Vertical Federated Learning (VFL) is a privacy-preserving distributed learning paradigm
where different parties collaboratively learn models using partitioned features of shared …
where different parties collaboratively learn models using partitioned features of shared …
A Data Poisoning Resistible and Privacy Protection Federated Learning Mechanism For Ubiquitous IoT
G Chen, X Li, L You, AM Abdelmoniem… - IEEE Internet of …, 2024 - ieeexplore.ieee.org
As a novel distributed learning paradigm, Federated Learning (FL) allows clients to train
global models collaboratively without exchanging private data. However, recent research …
global models collaboratively without exchanging private data. However, recent research …
Addressing data imbalance for federated recommender systems: a rebalancing framework with gradient alignment regularization
P Liu, G Lu - Journal of Intelligent Information Systems, 2024 - Springer
Federated recommender systems (FRSs) utilize decentralized data to offer personalized and
privacy-preserving recommendations. Existing studies on FRSs overlook the issue of data …
privacy-preserving recommendations. Existing studies on FRSs overlook the issue of data …
Self-Driven Entropy Aggregation for Byzantine-Robust Heterogeneous Federated Learning
Federated learning presents massive potential for privacy-friendly collaboration. However,
the performance of federated learning is deeply affected by byzantine attacks, where …
the performance of federated learning is deeply affected by byzantine attacks, where …