DQRE-SCnet: A novel hybrid approach for selecting users in Federated Learning with Deep-Q-Reinforcement Learning based on Spectral Clustering

  title={DQRE-SCnet: A novel hybrid approach for selecting users in Federated Learning with Deep-Q-Reinforcement Learning based on Spectral Clustering},
  author={Mohsen Ahmadi and Ali Taghavirashidizadeh and Danial Javaheri and Armin Masoumian and Saeid Jafarzadeh Ghoushchi and Yaghoub Pourasad},
  journal={J. King Saud Univ. Comput. Inf. Sci.},

A Review on Federated Learning and Machine Learning Approaches: Categorization, Application Areas, and Blockchain Technology

It was discovered that the best results were obtained from the hybrid design of an ML ensemble employing expert features, and novel FL applications should be investigated from the standpoint of the datasets and methodologies.

ML-DDoSnet: IoT Intrusion Detection Based on Denial-of-Service Attacks Using Machine Learning Methods and NSL-KDD

The most reliable and suitable solution for evaluating DDoS attacks in IoT is the BiLSTM design, which has chosen the safest instances with the highest accuracy among the models.

Machine Learning Methods for Intrusive Detection of Wormhole Attack in Mobile Ad-Hoc Network (MANET)

Based on the findings, the DT method's accuracy is 98.9% and higher than other methods, respectively, and in the next priority, SVM, KNN, CNN, LDA, and NB indicate high accuracy, respectively.

IAMnet: Presentation of Parallelization Approach for Repetitive Mining on Network Topologies with an Improved Apriori Method

This research proposes a parallelization-based approach to improve the performance of the Apriori algorithm in repetitive mining patterns on network topologies and concludes that this approach provides acceptable efficiency in terms of evaluation criteria such as energy consumption, network lifetime, and runtime compared to other methods.

DCNN-GCM: A Deep CNN and Granger Causality Models for Forecasting Welfare Level of Energy-Producing Countries and Evaluating the Relationship between Energy Consumption and Sustainable Economic Welfare

From the beginning of creation, human beings have realized the importance of energy for survival. They have always devoted a significant part of their energy to provide the required energy. Moreover,

Prediction and Classification of Financial Criteria of Management Control System in Manufactories Using Deep Interaction Neural Network (DINN) and Machine Learning

The management control system aids administrators in guiding a business toward its organizational plans; as a result, management control is primarily concerned with the execution of the plan and

Parallel operated hybrid Arithmetic-Salp swarm optimizer for optimal allocation of multiple distributed generation units in distribution networks

A parallel hybrid Arithmetic Optimization Algorithm and Salp Swarm Algorithm for the optimal sizing and placement of DGs in the Radial Distribution Networks (RDNs) and the proposed parallel hybrid AOASSA enables the mutual benefit of both algorithms.

Extend the lifetime of wireless sensor networks by modifying cluster-based data collection

This paper presents a clustering approach to reduce power consumption in wireless sensor networks, which is the most effective method for scalability and energy consumption reduction in sensor networks.

Analysis of the attack and its solution in wireless sensor networks

The security needs and security attacks in wireless sensor networks are outlined and the types of security attacks and their detection are focused on.



Optimizing Federated Learning on Non-IID Data with Reinforcement Learning

Favor, an experience-driven control framework that intelligently chooses the client devices to participate in each round of federated learning to counterbalance the bias introduced by non-IID data and to speed up convergence is proposed.

Federated Learning with Non-IID Data

This work presents a strategy to improve training on non-IID data by creating a small subset of data which is globally shared between all the edge devices, and shows that accuracy can be increased by 30% for the CIFAR-10 dataset with only 5% globally shared data.

Performance Analysis of Distributed and Federated Learning Models on Private Data

Robust and Communication-Efficient Federated Learning From Non-i.i.d. Data

Sparse ternary compression (STC) is proposed, a new compression framework that is specifically designed to meet the requirements of the federated learning environment and advocate for a paradigm shift in federated optimization toward high-frequency low-bitwidth communication, in particular in the bandwidth-constrained learning environments.

The Non-IID Data Quagmire of Decentralized Machine Learning

SkewScout is presented, a system-level approach that adapts the communication frequency of decentralized learning algorithms to the (skew-induced) accuracy loss between data partitions and it is shown that group normalization can recover much of the accuracy loss of batch normalization.

Towards Fair and Privacy-Preserving Federated Deep Models

A decentralized Fair and Privacy-Preserving Deep Learning (FPPDL) framework to incorporate fairness into federated deep learning models, and a local credibility mutual evaluation mechanism to guarantee fairness and a three-layer onion-style encryption scheme to guarantee both accuracy and privacy.

Privacy-Preserving Asynchronous Federated Learning Mechanism for Edge Network Computing

A Privacy-Preserving Asynchronous Federated Learning Mechanism for Edge Network Computing (PAFLM) is proposed, which can allow multiple edge nodes to achieve more efficient federated learning without sharing their private data.

Federated Machine Learning

This work introduces a comprehensive secure federated-learning framework, which includes horizontal federated learning, vertical federatedLearning, and federated transfer learning, and provides a comprehensive survey of existing works on this subject.

Survey on Federated Learning Towards Privacy Preserving AI

This paper presents in detail understanding of Federated Machine Learning, various federated architectures along with different privacy-preserving mechanisms, and depicts how Federated Learning is an emerging area of future research that would bring a new era in AI and Machine learning.