Rate distortion optimization for adaptive gradient quantization in federated learning
Federated Learning (FL) is an emerging machine learning framework designed to preserve privacy. However, the continuous updating of model parameters over uplink channels with limited throughput leads to a huge communication overload, which is a major challenge for FL. To address this issue, we propo...
Saved in:
| Main Authors: | Guojun Chen, Kaixuan Xie, Wenqiang Luo, Yinfei Xu, Lun Xin, Tiecheng Song, Jing Hu |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2024-12-01
|
| Series: | Digital Communications and Networks |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S235286482400018X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning With Adaptive Quantization and Differential Privacy
by: Emre Ardic, et al.
Published: (2025-01-01) -
Accelerating Energy-Efficient Federated Learning in Cell-Free Networks With Adaptive Quantization
by: Afsaneh Mahmoudi, et al.
Published: (2025-01-01) -
Temporal dependent rate-distortion optimization based on distortion backward propagation
by: Hongwei GUO, et al.
Published: (2022-12-01) -
Temporal dependent rate-distortion optimization based on distortion backward propagation
by: Hongwei GUO, et al.
Published: (2022-12-01) -
An Adaptive Approach in Channel Quantization for Small Cells Based on Per-Receiver Antenna Quantization
by: Sanjeeb Shrestha, et al.
Published: (2025-01-01)