Federated Deep

Federated deep learning (FL) addresses the challenge of training deep learning models on decentralized data, preserving data privacy while enabling collaborative model building across multiple clients. Current research focuses on improving model accuracy and efficiency in heterogeneous data settings, exploring techniques like adaptive obfuscation, knowledge distillation, and novel optimization algorithms tailored for federated architectures (e.g., proximal gradient descent, ADMM). This approach holds significant promise for various applications, including medical image analysis, IoT security, and personalized recommendations, by enabling the development of powerful models from sensitive data without compromising privacy.

Papers

December 5, 2022

FedUKD: Federated UNet Model with Knowledge Distillation for Land Use Classification from Satellite and Street Views
Renuga Kanagavelu, Kinshuk Dua, Pratik Garai, Susan Elias, Neha Thomas, Simon Elias, Qingsong Wei, Goh Siow Mong Rick, Liu Yong
Semantic Segmentation Knowledge Distillation Satellite Image Street View Federated Setting Federated Deep Federated Approach

December 1, 2022

Early prediction of the risk of ICU mortality with Deep Federated Learning
Korbinian Randl, Núria Lladós Armengol, Lena Mondrejevski, Ioanna Miliou
High Quality Risk Description Healthcare Data Early Prediction Federated Deep Intensive Care Unit Mortality

November 5, 2022

ON-DEMAND-FL: A Dynamic and Efficient Multi-Criteria Federated Learning Client Deployment Scheme
Mario Chahoud, Hani Sami, Azzam Mourad, Safa Otoum, Hadi Otrok, Jamal Bentahar, Mohsen Guizani
Decentralized Data Federated Deep Kubernetes Cluster Federated Learning Client Smartphone Data

October 16, 2022

FAQS: Communication-efficient Federate DNN Architecture and Quantization Co-Search for personalized Hardware-aware Preferences
Hongjiang Chen, Yang Wang, Leibo Liu, Shaojun Wei, Shouyi Yin
Federated Learning Neural Architecture Search Yes No Question User Preference Federated Deep Quantization Search

June 30, 2022

Privacy-preserving household load forecasting based on non-intrusive load monitoring: A federated deep learning approach
Xinxin Zhou, Jingru Feng, Jian Wang, Jianhong Pan
Deep Learning Approach Load Forecasting Non Intrusive Load Monitoring Federated Deep

June 3, 2022

Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification
Shuai Wang, Chengyang Li, Derrick Wing Kwan Ng, Yonina C. Eldar, H. Vincent Poor, Qi Hao, Chengzhong Xu
Autonomous Vehicle Product Design Verification Task Vehicular Network Federated Edge Learning Sensor Placement Autonomous Vehicle Perception Federated Deep Interactive Driving

May 26, 2022

Federated Non-negative Matrix Factorization for Short Texts Topic Modeling with Mutual Information
Shijing Si, Jianzong Wang, Ruiyi Zhang, Qinliang Su, Jing Xiao
Mutual Information Matrix Factorization Topic Model Short Text Federated Deep

May 11, 2022

eFedDNN: Ensemble based Federated Deep Neural Networks for Trajectory Mode Inference
Daniel Opoku Mensah, Godwin Badu-Marfo, Ranwa Al Mallah, Bilal Farooq
Diverse Ensemble Privacy Preserving Machine Learning GPS Trajectory Federated Deep Smart Mobility

November 27, 2021

Federated Deep Learning in Electricity Forecasting: An MCDM Approach
Marco Repetto, Davide La Torre, Muhammad Tariq
Multi Criterion Consumption Forecasting Multi Criterion Decision Federated Deep Explanation Output Electricity Forecasting

Federated Deep

Papers

FedUKD: Federated UNet Model with Knowledge Distillation for Land Use Classification from Satellite and Street Views

Early prediction of the risk of ICU mortality with Deep Federated Learning

ON-DEMAND-FL: A Dynamic and Efficient Multi-Criteria Federated Learning Client Deployment Scheme

FAQS: Communication-efficient Federate DNN Architecture and Quantization Co-Search for personalized Hardware-aware Preferences

Privacy-preserving household load forecasting based on non-intrusive load monitoring: A federated deep learning approach

Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification

Federated Non-negative Matrix Factorization for Short Texts Topic Modeling with Mutual Information

eFedDNN: Ensemble based Federated Deep Neural Networks for Trajectory Mode Inference

Federated Deep Learning in Electricity Forecasting: An MCDM Approach