HoloGraph: All-Optical Graph Learning via Light Diffraction

2026-02-07

AI Summary

This work proposes the first monolithic free-space all-optical graph neural network to overcome the efficiency limitations of existing physics-informed neural networks in graph-structured tasks, which struggle to achieve high-speed graph learning. By leveraging diffraction-based optical propagation and phase modulation, the architecture performs graph message passing at the speed of light and introduces an innovative optical skip connection to establish a domain-specific, fully optical end-to-end message-passing mechanism. This design breaks through the speed and energy-efficiency bottlenecks inherent in conventional digital graph neural networks. Experimental results on the Cora-ML and Citeseer datasets demonstrate classification performance comparable to or even surpassing that of digital GNNs, thereby validating the feasibility and superiority of all-optical graph learning.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

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.

Problem

• graph neural networks
• all-optical computing
• diffractive optics
• graph-structured data
• physics-based neural networks

Innovation

• all-optical graph neural network
• diffractive optical neural network
• optical message passing
• light diffraction
• graph learning