Search Results for author:
Found 30 papers, 11 papers with code
GeFL: Model-Agnostic Federated Learning with Generative Models
We empirically demonstrate the consistent performance gains of GeFL-F, while demonstrating better privacy preservation and robustness to a large number of clients.
Robust Bayesian Optimization via Localized Online Conformal Prediction
Bayesian optimization (BO) is a sequential approach for optimizing black-box objective functions using zeroth-order noisy observations.
Embedding Byzantine Fault Tolerance into Federated Learning via Virtual Data-Driven Consistency Scoring Plugin
By utilizing this scoring mechanism before the aggregation phase, the proposed plugin enables existing FL techniques to become robust against Byzantine attacks while maintaining their original benefits.
Generative AI-Powered Plugin for Robust Federated Learning in Heterogeneous IoT Networks
Federated learning enables edge devices to collaboratively train a global model while maintaining data privacy by keeping data localized.
ROK Defense M&S in the Age of Hyperscale AI: Concepts, Challenges, and Future Directions
Integrating hyperscale AI into national defense modeling and simulation (M&S) is crucial for enhancing strategic and operational capabilities.
Enhancing Battlefield Awareness: An Aerial RIS-assisted ISAC System with Deep Reinforcement Learning
This paper considers a joint communication and sensing technique for enhancing situational awareness in practical battlefield scenarios.
Reliable Sub-Nyquist Spectrum Sensing via Conformal Risk Control
Such existing solutions can only provide guarantees in terms of false negative rate (FNR) in the asymptotic regime of large held-out data sets.
RAQ-VAE: Rate-Adaptive Vector-Quantized Variational Autoencoder
Vector Quantized Variational AutoEncoder (VQ-VAE) is an established technique in machine learning for learning discrete representations across various modalities.
LR-FHSS Transceiver for Direct-to-Satellite IoT Communications: Design, Implementation, and Verification
This paper proposes a long range-frequency hopping spread spectrum (LR-FHSS) transceiver design for the Direct-to-Satellite Internet of Things (DtS-IoT) communication system.
Rate-splitting Multiple Access for Hierarchical HAP-LAP Networks under Limited Fronthaul
In this correspondence, we propose hierarchical high-altitude platform (HAP)-low-altitude platform (LAP) networks with the aim of maximizing the sum-rate of ground user equipments (UEs).
FedSplitX: Federated Split Learning for Computationally-Constrained Heterogeneous Clients
Foundation models (FMs) have demonstrated remarkable performance in machine learning but demand extensive training data and computational resources.
On the Temperature of Bayesian Graph Neural Networks for Conformal Prediction
Building on a recent work that introduced a scaling parameter for constructing valid credible regions from posterior estimate, our study explores the advantages of incorporating a temperature parameter into Bayesian GNNs within CP framework.
Cache-assisted Mobile Edge Computing over Space-Air-Ground Integrated Networks for Extended Reality Applications
Extended reality-enabled Internet of Things (XRI) provides the new user experience and the sense of immersion by adding virtual elements to the real world through Internet of Things (IoT) devices and emerging 6G technologies.
NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clients
Federated learning (FL) enables distributed training while preserving data privacy, but stragglers-slow or incapable clients-can significantly slow down the total training time and degrade performance.
Energy-Efficient Vehicular Edge Computing with One-by-one Access Scheme
With the advent of ever-growing vehicular applications, vehicular edge computing (VEC) has been a promising solution to augment the computing capacity of future smart vehicles.
Marine IoT Systems with Space-Air-Sea Integrated Networks: Hybrid LEO and UAV Edge Computing
Marine Internet of Things (IoT) systems have grown substantially with the development of non-terrestrial networks (NTN) via aerial and space vehicles in the upcoming sixth-generation (6G), thereby assisting environment protection, military reconnaissance, and sea transportation.
Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance
While being an effective framework of learning a shared model across multiple edge devices, federated learning (FL) is generally vulnerable to Byzantine attacks from adversarial edge devices.
Fast-Convergent Federated Learning via Cyclic Aggregation
Federated learning (FL) aims at optimizing a shared global model over multiple edge devices without transmitting (private) data to the central server.
Compressed Particle-Based Federated Bayesian Learning and Unlearning
Conventional frequentist FL schemes are known to yield overconfident decisions.
Hybrid UAV-enabled Secure Offloading via Deep Reinforcement Learning
Unmanned aerial vehicles (UAVs) have been actively studied as moving cloudlets to provide application offloading opportunities and to enhance the security level of user equipments (UEs).
Forget-SVGD: Particle-Based Bayesian Federated Unlearning
Variational particle-based Bayesian learning methods have the advantage of not being limited by the bias affecting more conventional parametric techniques.
Bayesian Variational Federated Learning and Unlearning in Decentralized Networks
Federated Bayesian learning offers a principled framework for the definition of collaborative training algorithms that are able to quantify epistemic uncertainty and to produce trustworthy decisions.
End-to-End Fast Training of Communication Links Without a Channel Model via Online Meta-Learning
The proposed approach is based on a meta-training phase in which the online gradient-based meta-learning of the decoder is coupled with the joint training of the encoder via the transmission of pilots and the use of a feedback link.
Cooperative Learning via Federated Distillation over Fading Channels
Cooperative training methods for distributed machine learning are typically based on the exchange of local gradients or local model parameters.
Signal Processing Distributed, Parallel, and Cluster Computing Information Theory Information Theory
From Learning to Meta-Learning: Reduced Training Overhead and Complexity for Communication Systems
Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations.
Meta-Learning to Communicate: Fast End-to-End Training for Fading Channels
When a channel model is available, learning how to communicate on fading noisy channels can be formulated as the (unsupervised) training of an autoencoder consisting of the cascade of encoder, channel, and decoder.
Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning
This paper considers an Internet-of-Things (IoT) scenario in which devices sporadically transmit short packets with few pilot symbols over a fading channel.
Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data
Cooperative training methods for distributed machine learning typically assume noiseless and ideal communication channels.
Learning How to Demodulate from Few Pilots via Meta-Learning
Consider an Internet-of-Things (IoT) scenario in which devices transmit sporadically using short packets with few pilot symbols.
Coded Federated Computing in Wireless Networks with Straggling Devices and Imperfect CSI
Distributed computing platforms typically assume the availability of reliable and dedicated connections among the processors.
Information Theory Information Theory
