Search Results for author:
Found 8 papers, 0 papers with code
Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space
Because FL algorithms hardly converge the parameters of machine learning (ML) models, this paper focuses on the convergence of ML models in function spaces.
Zero-Shot Adaptation for mmWave Beam-Tracking on Overhead Messenger Wires through Robust Adversarial Reinforcement Learning
Second, we demonstrate the feasibility of \textit{zero-shot adaptation} as a solution, where a learning agent adapts to environmental parameters unseen during training.
MAB-based Client Selection for Federated Learning with Uncertain Resources in Mobile Networks
This paper proposes a multi-armed bandit (MAB)-based client selection method to solve the exploration and exploitation trade-off and reduce the time consumption for FL in mobile networks.
Networking and Internet Architecture
Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data
To this end, based on the idea of leveraging an unlabeled open dataset, we propose a distillation-based semi-supervised FL (DS-FL) algorithm that exchanges the outputs of local models among mobile devices, instead of model parameter exchange employed by the typical frameworks.
Lottery Hypothesis based Unsupervised Pre-training for Model Compression in Federated Learning
The key idea of the proposed method is to obtain a ``good'' subnetwork from the original NN using the unlabeled data based on the lottery hypothesis.
Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noise
To this end, a differentially private AirComp-based FL is designed in this study, where the key idea is to harness receiver noise perturbation injected to aggregated global models inherently, thereby preventing the inference of clients' private data.
Networking and Internet Architecture Signal Processing
Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data
Therefore, to mitigate the degradation induced by non-IID data, we assume that a limited number (e. g., less than 1%) of clients allow their data to be uploaded to a server, and we propose a hybrid learning mechanism referred to as Hybrid-FL, wherein the server updates the model using the data gathered from the clients and aggregates the model with the models trained by clients.
Deep Reinforcement Learning-Based Channel Allocation for Wireless LANs with Graph Convolutional Networks
In densely deployed WLANs, the number of the available topologies of APs is extremely high, and thus we extract the features of the topological structures based on GCNs.
