HoloGraph: All-Optical Graph Learning via Light Diffraction

TL;DR

HoloGraph is a pioneering all-optical graph neural network system that uses light diffraction for fast, energy-efficient graph learning, demonstrating competitive performance on standard datasets.

Contribution

It introduces the first monolithic free-space all-optical GNN with a novel message-passing mechanism using optical diffraction and phase modulation.

Findings

Achieves light-speed message passing over graphs.

Shows competitive classification accuracy on Cora-ML and Citeseer datasets.

Demonstrates the effectiveness of optical diffraction in GNNs.

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.