ITW 2022 Federated Deep CSI Estimation Competition

In the context of the invited session “Communication-efficient gradient compression and coding in distributed learning”  at ITW, Yu-Chih (Jerry) Huang [NYCU], Shih-Chun Lin [NTU], and Stefano Rini [NYCU] will organize the following competition: 

Federated Deep learning for CSI estimation in Massive MIMO environments

Distributed machine learning methods are poised to drastically improve the performance of many aspects of communication engineering – from the physical layer to the application one – by leveraging the richness in the data collected at the user equipment. In this competition, we focus on the problem of federated training of a deep CSI compressor for massive MIMO in 5G protocols and beyond.

Objective:
A set of remote users observe a set of pilot signals as transmitted by a MIMO base station (BS) and are tasked with the distributed training of a compressor for the channel estimate. The training of this compressor occurs in a distributed manner, with the BS orchestrating the training and maintaining a centralized model. Training must occur within a set communication budget and model size. 

Data:
The data for training will be made available here soon as the competition opens. 

Important dates:

• Registration opens Aug 10, 2022
• Registration closes Sep 10, 2022
• Evaluation period begins Sep 20, 2022
• Competition results are announced Oct 1, 2022 

Registration: 
Registration will be open soon.