FedAvg
PulseAugur coverage of FedAvg — every cluster mentioning FedAvg across labs, papers, and developer communities, ranked by signal.
- instance of DagsHub 90%
- instance of alphaXiv 90%
- instance of Gotit.pub 90%
- instance of ScienceCast 90%
- instance of Federated Averaging 90%
- used by Gaussian mechanism 80%
- instance of federated learning 70%
- used by DagsHub 70%
- used by alphaXiv 70%
- competes with FedProx 70%
- used by CatalyzeX 70%
- used by CIFAR-10 70%
9 day(s) with sentiment data
-
New framework exposes privacy risks in federated LoRA-adapted Vision Transformers
Researchers have developed a new framework to address privacy risks in federated learning when using parameter-efficient fine-tuning methods like LoRA with Vision Transformers. The proposed spatially anchored generative…
-
Federated learning uses physical laws to secure critical infrastructure anomaly detection
Researchers have developed a novel federated learning approach that uses physical invariants, such as conservation of mass, to secure anomaly detection models in critical water infrastructure. This method allows operato…
-
LLMs dynamically select aggregation rules in federated learning
Researchers have developed FedReason, a novel approach that utilizes large language models (LLMs) to dynamically select aggregation rules in federated learning. Instead of relying on fixed rules, FedReason employs an LL…
-
Federated learning system FedXCrop enhances privacy in crop disease detection
Researchers have developed FedXCrop, a federated learning system designed for privacy-preserving crop disease detection. This system allows for the training of disease classification models without farms needing to shar…
-
Federated learning models can learn from static context for time series forecasting
A new research paper explores how federated learning models can effectively utilize static contextual information for time series forecasting. The study found that per-batch aggregation methods like FedAdam are superior…
-
CovFedAvg enhances federated learning model selection without calibration data
Researchers have introduced CovFedAvg, a novel method for federated model selection that aims to improve model compatibility across clients with differing data distributions. Unlike traditional FedAvg, CovFedAvg retains…
-
New framework enhances trust in collaborative AI systems
A new framework called Governance-Aware Federated Learning (GAFL) has been proposed to enhance trust and security in collaborative AI systems. This framework integrates independent verification of governance values, tem…
-
Federated learning framework enables privacy-preserving tabular-to-image encoding
Researchers have developed Fed-IGTD, a novel framework that utilizes federated learning to enable tabular-to-image encoding without centralizing sensitive data. This approach allows multiple clients to collaboratively t…
-
Federated Learning Framework Enhances RGB-X Tracking Accuracy
Researchers have developed Fed-MAPTrack, a novel federated learning framework designed for RGB-X tracking tasks. This approach addresses the challenge of training multimodal tracking models without centralizing sensitiv…
-
New FedStop framework optimizes local training epochs in federated learning
Researchers have developed a new framework called FedStop for federated learning, which optimizes the number of local training epochs on each client. Instead of using a fixed number of epochs, FedStop treats local train…
-
Federated learning vulnerable to privacy leaks and data poisoning attacks
A new report details the vulnerabilities of federated learning, a method for adapting pretrained models to local user data. Researchers found that a central server can recover private label sets from a single client upd…
-
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…
-
ERIS framework enhances federated learning privacy and scalability
Researchers have introduced ERIS, a new framework for federated learning designed to improve the balance between privacy, utility, and scalability. ERIS utilizes Federated Shard Aggregation (FSA) to partition client upd…
-
New protocol enhances privacy and robustness in federated intrusion detection
Researchers have developed PVBRF-ID, a novel two-server protocol designed for federated intrusion detection in oilfield enterprise networks. This system addresses the inherent trade-off between privacy and robustness in…
-
New method enables personalized AI model alignment across distributed agents
Researchers have introduced Personalized Federated Direct Preference Optimization (pFedDPO), a novel approach to align language models across distributed agents without centralizing sensitive data. Unlike previous metho…
-
Fed-GRPO enables privacy-preserving federated LLM training
Researchers have introduced Fed-GRPO, a novel federated learning framework designed for training large language models (LLMs) using reinforcement learning without compromising data privacy. This method utilizes reward s…
-
AI supervision effectiveness in fraud detection questioned in new study
A new study published on arXiv explores the effectiveness of AI supervision in network fraud decision management, proposing a Decider-Supervisor (DS) framework integrated with blockchain for auditability. The research e…
-
Federated learning framework adapts to low-resource medical imaging sites
Researchers have developed Fed-ADApt, a novel federated learning framework designed for medical image segmentation that accommodates varying computational resources across institutions. This approach allows lower-resour…
-
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…
-
RIPPLE framework offers offline clustering for federated learning
Researchers have developed RIPPLE, a novel framework for clustered federated learning designed to address client drift in non-IID data scenarios. Unlike previous methods that integrate cluster discovery within the train…