Skip to content

[INFOCOM 2026] Official codes for "ChannelMAE: Self-Supervised Learning Assisted Online Adaptation of Neural Channel Estimators"

Notifications You must be signed in to change notification settings

tesiawang/ChannelMAE

 
 

Repository files navigation

ChannelMAE: Self-Supervised Learning Assisted Online Adaptation of Neural Channel Estimators

This repository contains the implementation for our paper "ChannelMAE: Self-Supervised Learning Assisted Online Adaptation of Neural Channel Estimators" submitted to INFOCOM 2026.

Project Structure

ChannelMAE/
├── cebed/                         # Main package
│   ├── models/                    # Base model implementations
│   │   └── mae_random_mask.py     # Random mask MAE
│   ├── models_with_ssl/           # Self-supervised models
│   │   └── recon_net.py           # Main ChannelMAE implementation
│   ├── datasets_with_ssl/         # Dataset implementations
│   ├── online_ttt_v3.py           # Online adaptation scripts
│   ├── online_adapt_*.py          # Baseline adaptation scripts
│   └── ...
├── hyperparams/                   # Model hyperparameter configs
├── scripts/                       # Utility scripts
│   └── online_ttt.py              # Online TTT execution script
├── runs/                          # Training and evaluation scripts
└── ray_tracing_data/              # Ray tracing simulation data

Results and Figures

The experimental results and figures referenced in the paper are in: plot_figs/

Getting Started

  1. Pretraining ChannelMAE:
cd runs
bash pretrain.sh
  1. Online adaptation and evaluation:
bash ttt.sh
  1. Baseline evaluation:
bash eval_baselines.sh

License

This project is licensed under the same terms as the original CeBed project. Please refer to the CeBed repository for license details.

Acknowledgments

This codebase is built upon the excellent foundation provided by the CeBed project. We thank the original authors for their valuable contribution to the wireless communication community.

About

[INFOCOM 2026] Official codes for "ChannelMAE: Self-Supervised Learning Assisted Online Adaptation of Neural Channel Estimators"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 91.7%
  • Shell 5.2%
  • MATLAB 3.1%