Results 141 to 150 of about 1,993,316 (300)

Client selection for federated learning against label flipping attacks

物联网学报
Federated learning (FL) allows multiple clients to train a global model collaboratively by sharing only model updates without uploading local data. But due to its distributed global aggregation mode, FL is vulnerable to the malicious impact of label ...
LI Jianxin, CHEN Siguang
doaj   +2 more sources

SACW: Semi-Asynchronous Federated Learning with Client Selection and Adaptive Weighting

Computers
Federated learning (FL), as a privacy-preserving distributed machine learning paradigm, demonstrates unique advantages in addressing data silo problems.
Shuaifeng Li, Fangfang Shan, Shiqi Mao, Yanlong Lu, Fengjun Miao, Zhuo Chen   +5 more
doaj   +1 more source

Client selection in federated learning based on gradients importance

AIP Conference Proceedings
Federated learning (FL) enables multiple devices to collaboratively learn a global model without sharing their personal data. In real-world applications, the different parties are likely to have heterogeneous data distribution and limited communication bandwidth.
Ouiame Marnissi, Hajar El Hammouti, El Houcine Bergou   +2 more
openaire   +2 more sources

The Interoperability Challenge in DFT Workflows Across Implementations

Advanced Intelligent Discovery, EarlyView.
Interoperability and cross‐validation remain major challenges in the computational materials science. In this work, we introduce a common input/output standard that enables internal translation across multiple workflow managers—AiiDA, PerQueue, Pipeline Pilot, and SimStack—while producing results in a unified schema.
Simon K. Steensen, Tushar Singh Thakur, Manuel Dillenz, Johan M. Carlsson, Celso R. C. Rêgo, Eibar Flores, Hamidreza Hajiyani, Felix Hanke, Juan María García Lastra, Wolfgang Wenzel, Nicola Marzari, Tejs Vegge, Giovanni Pizzi, Ivano E. Castelli   +13 more
wiley   +1 more source

Quarterly report of the Client Security Fund Committee. 2017: Apr.-Jun. [PDF]

, 2017
Quarterly; Began in 2005?; "Pursuant to Practice Book [section] 2-72(e), the following is a report of the activities of the Client Security Fund Committee for ...
Connecticut. Client Security Fund Committee.
core  

FedBoost: Bayesian Estimation Based Client Selection for Federated Learning

IEEE Access
Although federated learning (FL) represents a distributed machine learning paradigm that ensures privacy protection, the failure of stragglers to upload local models in a timely manner results in an overall degradation of the global model’s ...
Yuhang Sheng, Lingguo Zeng, Shuqin Cao, Qing Dai, Shasha Yang, Jianfeng Lu   +5 more
doaj   +1 more source

An Autonomous Large Language Model‐Agent Framework for Transparent and Local Time Series Forecasting

Advanced Intelligent Discovery, EarlyView.
Architecture of the proposed large language model (LLM)‐based agent framework for autonomous time series forecasting in thermal power generation systems. The framework operates through a vertical pipeline initiated by natural language queries from users, which are processed by the LLM Agent Core powered by Llama.cpp and a ReAct loop with persistent ...
William Gouvêa Buratto, Gabriel Villarrubia Gonzalez, Ademir Nied, Laio Oriel Seman, Anne Carolina Rodrigues Klaar, Stefano Frizzo Stefenon   +5 more
wiley   +1 more source

Data‐Efficient Cycle‐Level Capacity Prediction Using 1D Deep Convolutional Network

Advanced Intelligent Discovery, EarlyView.
We introduce DeepBat, a deep learning framework featuring a 1D convolutional backbone designed to extract latent degradation patterns from a microstructurally diverse electrode dataset. By learning complex formulation–performance relationships, the model accurately predicts long‐term specific discharge capacity using limited early‐cycle data, providing
Tao Huang, Bing Sun, Zhigang Chen, Chenyu Zhao, Eugene Bakker, Yaojie Lei, Lingfei Zhao, Shijian Wang, Chao Liu, Virginia Xiaojun He, Bahram Shirzadi, Hao Liu, Xin Xi, Ruiliu Liu, Dongqing Wu, Guodong Long, Guoxiu Wang   +16 more
wiley   +1 more source

Quarterly report of the Client Security Fund Committee. 2009: Jan.-Mar. [PDF]

, 2009
Quarterly; Began in 2005?; "Pursuant to Practice Book [section] 2-72(e), the following is a report of the activities of the Client Security Fund Committee for ..."; Harvested from the web on 8/20 ...
Connecticut. Client Security Fund Committee.
core  

Federated Learning: A Survey of Core Challenges, Current Methods, and Opportunities

Computers
Federated learning (FL) has emerged as a transformative distributed learning paradigm that enables collaborative model training without sharing raw data, thereby preserving privacy across large, diverse, and geographically dispersed clients.
Madan Baduwal, Priyanka Paudel, Vini Chaudhary   +2 more
doaj   +1 more source