federated learning
PulseAugur coverage of federated learning — every cluster mentioning federated learning across labs, papers, and developer communities, ranked by signal.
- instance of Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy Constraints 95%
- instance of Gotit.pub 90%
- instance of CatalyzeX 90%
- instance of Decentralized federated learning system 90%
- instance of Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework 90%
- instance of Split Federated Learning 90%
- used by homomorphic encryption 90%
- used by differential privacy 80%
- used by optimal transport 80%
- used by alphaXiv 70%
- authored by alphaXiv 70%
- developed alphaXiv 70%
- 2026-05-22 research_milestone Publication of a paper detailing an embedding-based federated learning system for iron deficiency prediction. source
14 day(s) with sentiment data
-
New research explores Gibbs measures for machine learning and federated learning
This paper explores three operations on Gibbs probability measures relevant to machine learning. It details how renormalization, normalized log-linear combinations, and nested Gibbs measures can generate new Gibbs measu…
-
New federated soft clustering method uses GTVMin to link personalized GMMs
Researchers have developed a new method for federated soft clustering, which allows devices to train personalized Gaussian mixture models (GMMs) on their private data. The approach, termed Generalized Total Variation Mi…
-
Federated Learning Challenges Explored in New Paper
This item discusses a realistic problem within Federated Learning, focusing on the challenges faced by authors in this domain. It highlights the complexities and potential issues encountered when working with federated …
-
New FedASAP method enhances personalized federated learning for brain MRI segmentation
Researchers have developed FedASAP, a novel method for personalized federated learning in medical imaging. This approach uses activation statistics to guide adaptive model pruning, creating smaller, more efficient segme…
-
Federated Graph Neural Networks Harmed by Structural Differences
A new research paper investigates structural negative transfer in federated graph neural networks, a phenomenon where differing graph structures among participants harm model performance. The study found that a structur…
-
New framework optimizes federated learning for healthcare centers
Researchers have developed Adaptive Bayesian Partner Selection (ABPS), a peer-to-peer framework designed to improve federated learning in healthcare settings. This approach addresses challenges like data heterogeneity a…
-
Blockchain-coordinated federated learning marketplaces show amortizing costs
A new paper analyzes the lifecycle costs of federated learning marketplaces coordinated by smart contracts on a blockchain. The study found that while on-chain operations can be costly, the fixed deployment expenses amo…
-
New privacy defense prunes visual tokens for LLMs
Researchers have developed QPriv-VL, a novel framework designed to enhance privacy in Vision-Language Models (VLMs) used in sensitive applications like Federated Learning. This system intelligently prunes visual tokens …
-
Decentralized AI for 6G Networks: Trust, Explainability, and Sustainability
This paper proposes a framework for decentralized intelligence in future 6G networks, emphasizing the joint design of trustworthiness, explainability, and sustainability. It argues that traditional centralized AI approa…
-
FLoKD framework enables federated LLM training with reduced communication costs
Researchers have developed FLoKD, a novel framework for federated learning of large language models (LLMs) over wireless networks. This approach utilizes adaptive knowledge distillation by transmitting intermediate LoRA…
-
New VQA research explores answerability prediction, counterfactual learning, visual benchmarks, and privacy
Researchers are advancing Visual Question Answering (VQA) through several new approaches. One paper introduces VT-Transformer, which uses a Transformer architecture to predict answerability by analyzing visual and textu…
-
New Batched SGD method offers high-probability convergence guarantees
Researchers have introduced Batched SGD, a novel variant of stochastic gradient descent designed to achieve high-probability convergence guarantees for optimization problems. This method partitions online samples into e…
-
Federated learning communication time cost predicted for wireless networks
Researchers have developed a method to predict the communication time cost in federated learning scenarios over IEEE 802.11 wireless networks. By using ns-3 simulations to measure frame delivery ratios and saturation th…
-
New Fed-Equilibrium framework tackles knowledge dominance in clinical federated learning
Researchers have introduced Fed-Equilibrium, a novel framework designed to address the challenge of "knowledge dominance" in federated learning, particularly within multi-center clinical networks. This framework employs…
-
Federated learning challenge shows AI far from clinical viability in surgical vision
The FedSurg Challenge, a new initiative in federated learning for surgical vision, focused on appendicitis classification using laparoscopic appendectomy videos. Despite employing federated learning to address privacy c…
-
Federated learning method enhances fire detection robustness
Researchers have developed a new federated learning method for indoor fire detection that addresses limitations in bandwidth, client reliability, and server trust. The approach utilizes a rotating coordinator to enhance…
-
New \"$\alpha$-split\" method enhances privacy for speech LLMs in federated learning
Researchers have developed a new method called \"$\alpha$-split\" to improve differential privacy in federated learning for multilingual speech large language models (speech-LLMs). Standard per-layer differential privac…
-
New gradient inversion attack reveals significant privacy risks in federated learning
Researchers have developed a new method for gradient inversion attacks in federated learning, inspired by LT codes. This technique allows for exact recovery of training data and labels from a single round of FedSGD, sig…
-
Federated learning boosts cross-modality medical image segmentation
A new research paper explores federated learning techniques to improve cross-modality medical image segmentation, addressing challenges posed by data distributed across institutions and varying imaging protocols. The st…
-
Federated CLIP calibration issues highlighted in new research
A new research paper explores the calibration of vision-language models (VLMs) like CLIP when adapted using federated learning across decentralized data silos. The study found that common prompt-tuning methods often deg…