White-Box AI Model: Next Frontier of Wireless Communications
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910910477500416 |
|---|---|
| author | Yang, Jiayao Zhang, Jiayi Xu, Bokai Zheng, Jiakang Liu, Zhilong Liu, Ziheng Niyato, Dusit Debbah, Mérouane Han, Zhu Ai, Bo |
| author_facet | Yang, Jiayao Zhang, Jiayi Xu, Bokai Zheng, Jiakang Liu, Zhilong Liu, Ziheng Niyato, Dusit Debbah, Mérouane Han, Zhu Ai, Bo |
| contents | White-box AI (WAI), or explainable AI (XAI) model, a novel tool to achieve the reasoning behind decisions and predictions made by the AI algorithms, makes it more understandable and transparent. It offers a new approach to address key challenges of interpretability and mathematical validation in traditional black-box models. In this paper, WAI-aided wireless communication systems are proposed and investigated thoroughly to utilize the promising capabilities. First, we introduce the fundamental principles of WAI. Then, a detailed comparison between WAI and traditional black-box model is conducted in terms of optimization objectives and architecture design, with a focus on deep neural networks (DNNs) and transformer networks. Furthermore, in contrast to the traditional black-box methods, WAI leverages theory-driven causal modeling and verifiable optimization paths, thereby demonstrating potential advantages in areas such as signal processing and resource allocation. Finally, we outline future research directions for the integration of WAI in wireless communication systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09138 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | White-Box AI Model: Next Frontier of Wireless Communications Yang, Jiayao Zhang, Jiayi Xu, Bokai Zheng, Jiakang Liu, Zhilong Liu, Ziheng Niyato, Dusit Debbah, Mérouane Han, Zhu Ai, Bo Information Theory White-box AI (WAI), or explainable AI (XAI) model, a novel tool to achieve the reasoning behind decisions and predictions made by the AI algorithms, makes it more understandable and transparent. It offers a new approach to address key challenges of interpretability and mathematical validation in traditional black-box models. In this paper, WAI-aided wireless communication systems are proposed and investigated thoroughly to utilize the promising capabilities. First, we introduce the fundamental principles of WAI. Then, a detailed comparison between WAI and traditional black-box model is conducted in terms of optimization objectives and architecture design, with a focus on deep neural networks (DNNs) and transformer networks. Furthermore, in contrast to the traditional black-box methods, WAI leverages theory-driven causal modeling and verifiable optimization paths, thereby demonstrating potential advantages in areas such as signal processing and resource allocation. Finally, we outline future research directions for the integration of WAI in wireless communication systems. |
| title | White-Box AI Model: Next Frontier of Wireless Communications |
| topic | Information Theory |
| url | https://arxiv.org/abs/2504.09138 |