Abstract

Graph-based neural networks have promising perspectives but are limited by electronic bottlenecks. Our work explores the advantages of optical neural networks in the graph domain. We propose an optical graph neural network (OGNN) based on inverse-designed optical processing units (OPUs) to classify graphs with optics. The OPUs, combined with two types of optical components, can perform multiply–accumulate, matrix–vector multiplication, and matrix–matrix multiplication operations. The proposed OGNN can classify typical non-Euclidean MiniGCDataset graphs and successfully predict 1000 test graphs with 100% accuracy. The OPU-formed optical–electrical graph attention network is also scalable to handle more complex graph data, such as the Cora dataset, with 89.0% accuracy.

© 2022 Optica Publishing Group

Enhanced model iteration algorithm with graph neural network for diffuse optical tomography

Huangjian Yi, Ruigang Yang, Yishuo Wang, Yihan Wang, Hongbo Guo, Xu Cao, Shouping Zhu, and Xiaowei He
Biomed. Opt. Express 15(3) 1910-1925 (2024)

Network-aware compute and memory allocation in optically composable data centers with deep reinforcement learning and graph neural networks

Zacharaya Shabka and Georgios Zervas
J. Opt. Commun. Netw. 15(2) 133-143 (2023)

Supervised graph convolution networks for OSNR and power estimation in optical mesh networks

Anurag Prakash and Subrat Kar
J. Opt. Commun. Netw. 14(6) 469-480 (2022)

Edge-enhanced graph neural network for DU-CU placement and lightpath provision in X-Haul networks

Ruikun Wang, Jiawei Zhang, Zhiqun Gu, Shuangyi Yan, Yuming Xiao, and Yuefeng Ji
J. Opt. Commun. Netw. 14(10) 828-839 (2022)

Lensless facial recognition with encrypted optics and a neural network computation

Ming-Hsuan Wu, Ya-Ti Chang Lee, and Chung-Hao Tien
Appl. Opt. 61(26) 7595-7601 (2022)