HoloGraph: All-Optical Graph Learning via Light Diffraction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908819802554368 |
|---|---|
| author | Li, Yingjie Zhou, Shanglin Ding, Caiwen Yu, Cunxi |
| author_facet | Li, Yingjie Zhou, Shanglin Ding, Caiwen Yu, Cunxi |
| contents | As a representative of next-generation device/circuit technology beyond CMOS, physics-based neural networks such as Diffractive Optical Neural Networks (DONNs) have demonstrated promising advantages in computational speed and energy efficiency. However, existing DONNs and other physics-based neural networks have mostly focused on exploring their machine intelligence, with limited studies in handling graph-structured tasks. Thus, we introduce HoloGraph, the first monolithic free-space all-optical graph neural network system. It proposes a novel, domain-specific message-passing mechanism with optical skip channels integrated into light propagation for the all-optical graph learning. HoloGraph enables light-speed optical message passing over graph structures with diffractive propagation and phase modulations. Our experimental results with HoloGraph, conducted using standard graph learning datasets Cora-ML and Citeseer, show competitive or even superior classification performance compared to conventional digital graph neural networks. Comprehensive ablation studies demonstrate the effectiveness of the proposed novel architecture and algorithmic methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07724 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HoloGraph: All-Optical Graph Learning via Light Diffraction Li, Yingjie Zhou, Shanglin Ding, Caiwen Yu, Cunxi Emerging Technologies As a representative of next-generation device/circuit technology beyond CMOS, physics-based neural networks such as Diffractive Optical Neural Networks (DONNs) have demonstrated promising advantages in computational speed and energy efficiency. However, existing DONNs and other physics-based neural networks have mostly focused on exploring their machine intelligence, with limited studies in handling graph-structured tasks. Thus, we introduce HoloGraph, the first monolithic free-space all-optical graph neural network system. It proposes a novel, domain-specific message-passing mechanism with optical skip channels integrated into light propagation for the all-optical graph learning. HoloGraph enables light-speed optical message passing over graph structures with diffractive propagation and phase modulations. Our experimental results with HoloGraph, conducted using standard graph learning datasets Cora-ML and Citeseer, show competitive or even superior classification performance compared to conventional digital graph neural networks. Comprehensive ablation studies demonstrate the effectiveness of the proposed novel architecture and algorithmic methods. |
| title | HoloGraph: All-Optical Graph Learning via Light Diffraction |
| topic | Emerging Technologies |
| url | https://arxiv.org/abs/2602.07724 |