FEMNIST
PulseAugur coverage of FEMNIST — every cluster mentioning FEMNIST across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New Clustered Federated Learning framework boosts 6G network efficiency
Researchers have developed a Clustered Federated Learning (CFL) framework to improve the efficiency and performance of distributed learning in future 6G networks, particularly when dealing with non-IID data. This framew…
-
New RoCo-FL framework boosts federated learning robustness against noise and heterogeneity
Researchers have introduced RoCo-FL, a novel framework designed to enhance the robustness and convergence of Over-the-Air Federated Learning (OTA-FL) systems. This framework specifically addresses challenges posed by ch…
-
New Clustered Federated Learning method combats model collapse
Researchers have developed a new framework for Clustered Federated Learning (CFL) to address the issue of cluster collapse, where some models receive no updates. By modeling CFL as a control problem for a dynamical syst…
-
Translation training programs rapidly adopt generative AI tools
A survey of postgraduate translation training programs reveals a rapid adoption of generative AI tools and a shift towards cloud-based software. The study, conducted under the EMT Network but with broader participation,…
-
New mechanisms incentivize data contribution in federated learning
A new research paper introduces three mechanisms designed to incentivize data contribution in federated learning scenarios. The proposed methods, UPBReD, 2P-UPBReD, and T-2P-UPBReD, aim to ensure that strategic data own…
-
New method certifies sequential machine unlearning with performance guarantees
Researchers have developed a new method for certifying machine unlearning, particularly for sequential deletion requests. This approach ensures that a model, after data has been removed, remains close to a model that wa…
-
New PI-SME method enhances gradient inversion attacks in federated learning
Researchers have developed a new method called the Path-Integral Surrogate Model Extension (PI-SME) to improve gradient inversion attacks in federated learning. This technique treats a client's model update as a path in…
-
New HiFedProx method enhances federated learning regularization
Researchers have developed a new regularization technique called HiFedProx for federated learning, which improves upon the existing FedProx method. HiFedProx replaces the quadratic penalty with a power-type regularizer …
-
New attacks target federated GANs with label flipping and oversampling
Researchers have detailed new adversarial attacks targeting federated learning setups for Generative Adversarial Networks (GANs). These attacks involve malicious clients manipulating data by flipping labels or oversampl…
-
Federated Learning uses spectral entropy for data-free client contribution estimation
Researchers have developed a novel method for estimating client contributions in Federated Learning without requiring access to client data. This approach utilizes the spectral entropy of final-layer updates to measure …