Dynamic ensemble inference at the edge
M Merluzzi, A Martino, F Costanzo… - 2021 IEEE Global …, 2021 - ieeexplore.ieee.org
We propose a dynamic resource allocation algorithm in the context of future wireless
networks endowed with edge computing, to enable accurate energy efficient classification …
networks endowed with edge computing, to enable accurate energy efficient classification …
Joint Task Offloading and Resource Allocation for Quality-Aware Edge-Assisted Machine Learning Task Inference
Edge computing is essential to enhance delay-sensitive and computation-intensive machine
learning (ML) task inference services. Quality of inference results, which is mainly impacted …
learning (ML) task inference services. Quality of inference results, which is mainly impacted …
Accelerated Federated Learning Over Wireless Fading Channels With Adaptive Stochastic Momentum
Federated learning, as a well-known framework for collaborative training among distributed
local sensors and devices, has been widely used in practical learning applications. To …
local sensors and devices, has been widely used in practical learning applications. To …
DIN: A decentralized inexact Newton algorithm for consensus optimization
This paper tackles a challenging decentralized consensus optimization problem defined
over a network of interconnected devices. The devices work collaboratively to solve a …
over a network of interconnected devices. The devices work collaboratively to solve a …
Communication-efficient and privacy-preserving large-scale federated learning counteracting heterogeneity
X Zhou, G Yang - Information Sciences, 2024 - Elsevier
Federated learning is a commonly distributed framework for large-scale learning, where a
model is learned over massively distributed remote devices without sharing information on …
model is learned over massively distributed remote devices without sharing information on …
Network Sliced Distributed Learning-as-a-Service for Internet of Vehicles Applications in 6G Non-Terrestrial Network Scenarios
In the rapidly evolving landscape of next-generation 6G systems, the integration of AI
functions to orchestrate network resources and meet stringent user requirements is a key …
functions to orchestrate network resources and meet stringent user requirements is a key …
Maximin Design of Wideband Constant Modulus Waveform for Distributed Precision Jamming
Distributed precision jamming (DPJ) is an efficient way to control the combined power
spectrum (CPS) of both target and friendly devices in electronic warfare. However, the …
spectrum (CPS) of both target and friendly devices in electronic warfare. However, the …
Federated Learning and Meta Learning: Approaches, Applications, and Directions
Over the past few years, significant advancements have been made in the field of machine
learning (ML) to address resource management, interference management, autonomy, and …
learning (ML) to address resource management, interference management, autonomy, and …
[HTML][HTML] HSAC-ALADMM: an asynchronous lazy ADMM algorithm based on hierarchical sparse allreduce communication
D Wang, Y Lei, J Xie, G Wang - The Journal of Supercomputing, 2021 - Springer
The distributed alternating direction method of multipliers (ADMM) is an effective algorithm
for solving large-scale optimization problems. However, its high communication cost limits its …
for solving large-scale optimization problems. However, its high communication cost limits its …
Secure Aggregation in Heterogeneous Federated Learning for Digital Ecosystems
Privacy-preserving federated learning (PPFL) is vital for Industry 5.0 digital ecosystems due
to the increasing number of interconnected devices and the volume of shared sensitive data …
to the increasing number of interconnected devices and the volume of shared sensitive data …