One Pixel Image and RF Signal Based Split Learning for mmWave Received Power Prediction
By Yusuke Koda, Jihong Park, Medhi Bennis, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura. 2019
20 citations recorded by the source corpus.
Focusing on the received power prediction of millimeter-wave (mmWave) radio-frequency (RF) signals, we propose a multimodal split learning (SL) framework that integrates RF received signal powers and depth-images observed by physically separated entities. To improve its communication efficiency while preserving data privacy, we propose an SL neural network architecture that compresses the communication payload, i.e., images. Compared to a baseline solely utilizing RF signals, numerical results show that SL integrating only one pixel image with RF signals achieves higher prediction accuracy while maximizing both communication efficiency and privacy guarantees.
Subfields: Artificial Intelligence, Electrical and Electronic Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Medhi Bennis
- Jihong Park
- Anis Elgabli
- Praneeth Vepakomma
- Ramesh Raskar
- Abhishek Singh
- Sumudu Samarakoon
- Otkrist Gupta
In Electrical and Electronic Engineering
- Medhi Bennis
- Sumudu Samarakoon
- Jihong Park
- Anis Elgabli
- Mohamed K. Abdel-Aziz
- Takayuki Nishio
- Merouane Debbah
- Otkrist Gupta
Citations in the corpus
- NoPeek: Information leakage reduction to share activations in distributed deep learning (2020, methodology): “Split learning has been adopted in Internet of Things (IOT) and edgedevice machine learning settings in [20, 21, 22, 23] including multi-modal fusion based machine learning across edge devices in [24, 25] with data collected at the edge on imagery and millimeter wave (mmWave) radio frequency (RF) si”
- Extreme URLLC: Vision, Challenges, and Key Enablers (2020, methodology): “SL can effectively fuse multiple modalities by applying different data-specific architectures to the lower segment, while balancing the aggregating weights at the upper segment [10].”