Data and channel-adaptive sensor scheduling for federated edge learning via over-the-air gradient aggregation
Over-the-air gradient aggregation and data-aware scheduling have recently drawn great
attention due to the outstanding performance in improving communication efficiency for …
attention due to the outstanding performance in improving communication efficiency for …
Training time minimization for federated edge learning with optimized gradient quantization and bandwidth allocation
Training a machine learning model with federated edge learning (FEEL) is typically time
consuming due to the constrained computation power of edge devices and the limited …
consuming due to the constrained computation power of edge devices and the limited …
Predictive UAV base station deployment and service offloading with distributed edge learning
In modern networks, edge computing will be responsible for processing and learning from
the critical network-and user-generated data, such as wireless link usage, mobility …
the critical network-and user-generated data, such as wireless link usage, mobility …
Energy-efficient federated edge learning with joint communication and computation design
This paper studies a federated edge learning system, in which an edge server coordinates a
set of edge devices to train a shared machine learning (ML) model based on their locally …
set of edge devices to train a shared machine learning (ML) model based on their locally …
Optimizing aggregation frequency for hierarchical model training in heterogeneous edge computing
Federated Learning (FL) has been widely used for distributed machine learning in edge
computing. In FL, the model parameters are iteratively aggregated from the clients to a …
computing. In FL, the model parameters are iteratively aggregated from the clients to a …
E-tree learning: A novel decentralized model learning framework for edge ai
Traditionally, Artificial Intelligence (AI) models are trained on the central cloud with data
collected from end devices. This leads to high communication cost, long response time, and …
collected from end devices. This leads to high communication cost, long response time, and …
Gradient and channel aware dynamic scheduling for over-the-air computation in federated edge learning systems
To satisfy the expected plethora of computation-heavy applications, federated edge learning
(FEEL) is a new paradigm featuring distributed learning to carry the capacities of low-latency …
(FEEL) is a new paradigm featuring distributed learning to carry the capacities of low-latency …
Cost-efficient continuous edge learning for artificial intelligence of things
The accelerating convergence of artificial intelligence (AI) and Internet of Things (IoT) has
sparked a recent wave of interest in Artificial Intelligence of Things (AIoT). By exploiting the …
sparked a recent wave of interest in Artificial Intelligence of Things (AIoT). By exploiting the …
Fine-grained offloading for multi-access edge computing with actor-critic federated learning
KH Liu, YH Hsu, WN Lin, W Liao - 2021 IEEE Wireless …, 2021 - ieeexplore.ieee.org
In this paper, we study fine-grained offloading for multi-access edge computing (MEC) in 5G.
Existing works for computation offloading is on a per-task basis and do not take into account …
Existing works for computation offloading is on a per-task basis and do not take into account …
Scheduling for cellular federated edge learning with importance and channel awareness
In cellular federated edge learning (FEEL), multiple edge devices holding local data jointly
train a neural network by communicating learning updates with an access point without …
train a neural network by communicating learning updates with an access point without …