FLRF: Federated recommendation optimization for long-tail data distribution by Zaigang Gong, Siyu Chen, Qiangsheng Dai, Ying Feng, Jinghui Zhang

“…Federated learning allows training recommendation systems without revealing users’ private data, thereby protecting user privacy. …”
Get full text

Dynamic Ensemble Selection for EEG Signal Classification in Distributed Data Environments by Małgorzata Przybyła-Kasperek, Jakub Sacewicz

“…We propose a framework where classifiers are trained locally on independent subsets of EEG data without requiring centralized access. …”
Get full text

Strategy-Switch: From All-Reduce to Parameter Server for Faster Efficient Training by Nikodimos Provatas, Iasonas Chalas, Ioannis Konstantinou, Nectarios Koziris

“…However, the abundance of available data presents a challenge when training neural networks on a single node. …”
Get full text

Network modal innovation for distributed machine learning by Zehua GUO, Haowen ZHU, Tongwen XU

“…Distributed machine learning, as a popular computing architecture for artificial intelligence, still faces challenges of slow model training and poor data performance transmission.Traditional network modalities were un able to meet the communication needs of distributed machine learning scenarios, hindering the improvement of model training performance.New network modalities and operation logic for distributed machine learning scenarios using multimodal network technology were proposed.This approach was designed based on application characteristics and provides implications for the use of multimodal network technology in various industries.…”
Get full text

Survey of split learning data privacy by QIN Yiqun, MA Xiaojing, FU Jiayun, HU Pingyi, XU Peng, JIN Hai

“…Split learning, a privacy-preserving machine learning technique that enables the training of distributed models among multiple participants without sharing raw data, has emerged as a research focus. …”
Get full text

Comprehensive review of federated learning challenges: a data preparation viewpoint by Nawraz Saeed, Mohamed Ashour, Maggie Mashaly

“…Abstract Machine learning model accuracy, generalization, and reliability are greatly affected by the training data quality. High-quality data-characterized by completeness, consistency, accuracy, representativeness and homogeneity enables meaningful pattern learning and robust prediction. …”
Get full text

Enhancing Distributed Machine Learning through Data Shuffling: Techniques, Challenges, and Implications by Zhang Zikai

“…In distributed machine learning, data shuffling is a crucial data preprocessing technique that significantly impacts the efficiency and performance of model training. …”
Get full text

Generative adversarial networks for creating realistic training data for machine learning-based segmentation of FIB tomography data by Trushal Sardhara, Christian J Cyron, Martin Ritter, Roland C Aydin

“…This motivates the use of synthetic training data generated with Monte Carlo simulations of the FIB tomography process. …”
Get full text

State Estimation Method for Distribution Network Based on Incomplete Measurement Data by Peng LI, Wenjing ZU, Yixin LIU, Chunzheng TIAN, Yuanzhao HAO, Huixuan LI

“…In the online state estimation phase, the state estimation is performed online with incomplete real-time data of the distribution network and the trained CNN-LSTM model. …”
Get full text

Specialist training in general practice: Developments in social-legislation-based support – a data-driven introduction by Rass, Simon, Weber, Charlotte, Gibis, Bernhard

Subjects: “…physicians, family – supply & distribution…”
Get full text

Combining Physical and Network Data for Attack Detection in Water Distribution Networks by Côme Frappé - - Vialatoux, Pierre Parrend

“…However, current machine learning models do not fully take into account this cyber-physical component, being only trained either on the physical or on the network data. …”
Get full text

RODA-OOD: Robust Domain Adaptation from Out-of-Distribution Data by Jaekyun Jeong, Mangyu Lee, Sunguk Yun, Keejun Han, Jungeun Kim

“…RODA-OOD utilizes the characteristics of deep learning models that prioritize learning in-distribution data, which are easier to train on compared to OOD data. …”
Get full text

Knowledge-data-driven power flow calculation for lowvoltage active distribution network considering gray data by LIU Siliang, ZHENG Zenan, ZHANG Yongjun, YI Yingqi, CHI Yuquan

“…Finally, aiming at the problem that gray data (data containing measurement errors and outliers) used for training will affect model performance, an improved denoising autoencoder (DAE) is proposed to filter and eliminate anomalous samples. …”
Get full text

Memory-Efficient Batching for Time Series Transformer Training: A Systematic Evaluation by Phanwadee Sinthong, Nam Nguyen, Vijay Ekambaram, Arindam Jati, Jayant Kalagnanam, Peeravit Koad

“…Transformer-based time series models are being increasingly employed for time series data analysis. However, their training remains memory intensive, especially with high-dimensional data and extended look-back windows, while model-level memory optimizations are well studied, the batch formation process remains an underexplored factor to performance inefficiency. …”
Get full text

Detection and classification of lung diseases in distributed environment by Thuong-Cang Phan, Anh-Cang Phan

“…This research presents the detection and prediction of lung diseases using big data and deep learning techniques. In this work, we train neural networks based on Faster R-CNN and RetinaNet with different backbones (ResNet, CheXNet, and Inception ResNet V2) for lung disease classification in a distributed and parallel processing environment. …”
Get full text

Mechanism–Data Collaboration for Characterizing Sea Clutter Properties and Training Sample Selection by Wenhao Chen, Yong Zou, Zhengzhou Li, Shengrong Zhong, Haolin Gan, Aoran Li

“…The experiments based on field data are included to evaluate the effectiveness of the proposed method including sea clutter characterization accuracy and training sample selection across various scenarios. …”
Get full text

Mixed-Embeddings and Deep Learning Ensemble for DGA Classification With Limited Training Data by Christian Morbidoni, Alessandro Cucchiarelli, Luca Spalazzi

Get full text

Training data in satellite image classification for land cover mapping: a review by Daniel Moraes, Manuel L. Campagnolo, Mário Caetano

“…Hence, training data have a critical influence on classification accuracy. …”
Get full text

Distributed Collaborative Data Processing Framework for Unmanned Platforms Based on Federated Edge Intelligence by Siyang Liu, Nanliang Shan, Xianqiang Bao, Xinghua Xu

“…At the beginning of model training, random sampling is conducted from the public dataset and distributed to each unmanned platform, so as to mitigate the impact of data distribution heterogeneity and class imbalance during collaborative data processing in unmanned platforms. …”
Get full text

A Remedy for Heterogeneous Data: Clustered Federated Learning with Gradient Trajectory by Ruiqi Liu, Songcan Yu, Linsi Lan, Junbo Wang, Krishna Kant, Neville Calleja

Get full text