Edge-computing
54 papers with code • 1 benchmarks • 1 datasets
Deep Learning on EDGE devices
Benchmarks
| Trend | Dataset | Best Model | Paper Title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
DPED
Greatest papers with code
Spectral Pruning for Recurrent Neural Networks
zalandoresearch/fashion-mnist
•
•
Pruning techniques for neural networks with a recurrent architecture, such as the recurrent neural network (RNN), are strongly desired for their application to edge-computing devices.
DRLE: Decentralized Reinforcement Learning at the Edge for Traffic Light Control in the IoV
To this end, we propose a Decentralized Reinforcement Learning at the Edge for traffic light control in the IoV (DRLE).
Ranked #1 on
Edge-computing
on 0
Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-Constrained Edge Computing Systems
yoshitomo-matsubara/torchdistill
•
•
In this paper, we propose to modify the structure and training process of DNN models for complex image classification tasks to achieve in-network compression in the early network layers.
Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks
yoshitomo-matsubara/torchdistill
•
•
However, poor conditions of the wireless channel connecting the mobile devices to the edge servers may degrade the overall capture-to-output delay achieved by edge offloading.
Split Computing for Complex Object Detectors: Challenges and Preliminary Results
yoshitomo-matsubara/torchdistill
•
•
Following the trends of mobile and edge computing for DNN models, an intermediate option, split computing, has been attracting attentions from the research community.
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time Systems
yoshitomo-matsubara/torchdistill
•
•
Offloading the execution of complex Deep Neural Networks (DNNs) models to compute-capable devices at the network edge, that is, edge servers, can significantly reduce capture-to-output delay.
Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach
swordest/mec_drl
•
•
Numerical results are illustrated to demonstrate that efficient policies can be learned at each user, and performance of the proposed DDPG based decentralized strategy outperforms the conventional deep Q-network (DQN) based discrete power control strategy and some other greedy strategies with reduced computation cost.
On the Convergence of FedAvg on Non-IID Data
lx10077/fedavgpy
•
•
ICLR 2020
In this paper, we analyze the convergence of \texttt{FedAvg} on non-iid data and establish a convergence rate of $\mathcal{O}(\frac{1}{T})$ for strongly convex and smooth problems, where $T$ is the number of SGDs.
DeepShift: Towards Multiplication-Less Neural Networks
This family of neural network architectures (that use convolutional shifts and fully connected shifts) is referred to as DeepShift models.
Adaptive Federated Learning in Resource Constrained Edge Computing Systems
IBM/adaptive-federated-learning
•
•
Our focus is on a generic class of machine learning models that are trained using gradient-descent based approaches.