README.md

Attention-aware Resource Allocation and QoE Analysis for Metaverse xURLLC Services

This repository contains the code accompanying the paper:

"Attention-aware Resource Allocation and QoE Analysis for Metaverse xURLLC Services"

Authored by Hongyang Du, Jiazhen Liu, Dusit Niyato, Jiawen Kang, Zehui Xiong, Junshan Zhang, and Dong In Kim, accepted by IEEE JSAC.

The paper can be found at ArXiv.

---

🔧 Environment Setup

To create a new conda environment, execute the following command:

conda create --name aqoe python==3.10

⚡Activate Environment

Activate the created environment with:

conda activate aqoe

📦 Install Required Packages

The following package can be installed using pip:

pip install eals

🏃‍♀️ Run the Program

Run main.py in the file Main to start the program.

🔍 Check the results

Please refer to here to check the details abouth the User-Object-Attention Level (UOAL) dataset.

After generating randomly the sparse user-object-attention matrix, please put the 'my_rating.csv' under 'Seg2Rating' file.

Run main.py in the file Main. Then the predicted user-object attention values can be obtained and saved as 'pred.txt'

The compare between the predicted values and the ground truth values is shown as

📚 Acknowledgement

As we claimed in our paper, this repository used the codes in the following paper:

eALS: A Python implementation of the element-wise alternating least squares (eALS) for fast online matrix factorization
GitHub: https://github.com/newspicks/eals

Please consider to cite eALS if their codes are used in your research.

---

Citation

@article{du2023attention,
  title={Attention-aware resource allocation and QoE analysis for metaverse xURLLC services},
  author={Du, Hongyang and Liu, Jiazhen and Niyato, Dusit and Kang, Jiawen and Xiong, Zehui and Zhang, Junshan and Kim, Dong In},
  journal={IEEE Journal on Selected Areas in Communications},
  year={2023},
  publisher={IEEE}
}