FedProx
PulseAugur coverage of FedProx — every cluster mentioning FedProx across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
Federated learning struggles with temporal data in clinical AI models
Researchers have explored trajectory heterogeneity in federated world model learning, focusing on clinical prediction tasks using the MIMIC-IV dataset. Their study reveals that client ownership and participation signifi…
-
New analysis explores federated learning for Mamba2 state space models
Researchers have developed new convergence analysis for federated learning algorithms applied to selective state space models (SSMs), such as Mamba2. Existing federated learning methods are largely architecture-agnostic…
-
New Agentic Federated Learning Framework Enhances Adaptive Training
Researchers have introduced Agentic Federated Learning (AFL), a new framework that enhances traditional federated learning by incorporating autonomous agents. These agents, a Client-Side Agent (CSA) and a Server-Side Or…
-
New DP-FedProx framework enhances privacy in telecom churn prediction
Researchers have developed a new framework called DP-FedProx to address customer churn prediction in telecommunication networks. This framework utilizes differentially private federated proximal optimization, allowing m…
-
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 …
-
OmniMed-FL framework enables secure multimodal analysis of medical data
Researchers have developed OmniMed-FL, a multimodal federated learning framework designed to securely analyze medical imaging and patient records simultaneously. This approach addresses the challenges posed by regulatio…
-
Federated LoRA enables collaborative BiomedCLIP training across international X-ray cohorts
Researchers have developed a federated learning approach using Low-Rank Adaptation (LoRA) to train a BiomedCLIP model for chest X-ray classification across four international cohorts. This method allows institutions to …
-
New research highlights vulnerabilities in federated learning systems · 2 sources tracked
Researchers have developed new frameworks to address security vulnerabilities in federated learning systems. One method, STAIN-FL, introduces stealthy, contextually triggered backdoor attacks in video anomaly detection …
-
Federated learning framework enhances parametric insurance for renewable energy losses
Researchers have developed a federated learning framework to design parametric insurance indices for renewable energy production losses. This approach allows producers to model their losses locally using private data an…
-
New federated learning strategies tackle data heterogeneity and security threats · 5 sources tracked
Researchers are developing new federated learning (FL) strategies to address challenges like data heterogeneity and security threats. FedImp and FedTVD aim to improve convergence speed and model accuracy by weighting cl…
-
FedChronos enables privacy-preserving federated fine-tuning of time-series models
Researchers have developed FedChronos, a novel framework for federated fine-tuning of time-series foundation models (TSFMs) like Chronos-T5. This approach enables adaptation of TSFMs in decentralized settings where data…
-
New pipeline enhances privacy and accuracy for clinical AI models
Researchers have developed a robust pipeline for differentially private federated learning on imbalanced clinical data, specifically for cardiovascular risk prediction. The pipeline integrates the SMOTETomek technique t…
-
Federated Learning Strategies Compared for Clinical Mortality Prediction
Researchers have benchmarked several federated learning strategies for predicting in-hospital mortality using the MIMIC-IV dataset. The study found that FedProx performed best in terms of AUC-ROC and AUC-PR, outperformi…
-
Federated learning accuracy can hide critical model failures, study finds
A research project comparing federated learning algorithms for network intrusion detection revealed that high global accuracy can mask poor performance on minority data silos. The study found that FedAvg achieved 96% gl…
-
New FDRMFL framework enhances multimodal federated regression on non-IID data
Researchers have introduced FDRMFL, a novel framework designed for multimodal feature extraction in federated regression tasks, particularly addressing challenges posed by non-independent and identically distributed (no…
-
TallyTrain protocol slashes federated learning communication costs
Researchers have developed TallyTrain, a novel federated learning protocol designed to significantly reduce communication overhead. This method transmits only the predicted class index for each probe, rather than full s…
-
Federated learning shows promise for healthcare survival analysis · 2 sources tracked
A new paper evaluates federated learning for survival analysis in healthcare, specifically on breast cancer data across multiple institutions. The study compared three survival models (Cox Proportional Hazards, DeepSurv…
-
New framework enhances EV battery intelligence with decentralized federated learning
A new research paper introduces ABC-DFL, a decentralized federated learning framework designed for electric vehicle (EV) battery intelligence. This system aims to enhance security and trust by replacing traditional cent…
-
ChainLearn framework uses blockchain for capacity-aware federated learning
Researchers have developed ChainLearn, a new framework for federated ensemble learning that addresses the challenge of varying computational capacities among participating institutions. This system uses blockchain techn…
-
NVIDIA FLARE tutorial compares FedAvg and FedProx on non-IID data
This tutorial demonstrates how to implement and compare the FedAvg and FedProx federated learning algorithms using NVIDIA FLARE. The experiment utilizes a non-IID CIFAR-10 dataset, simulated by partitioning data with a …