Photonic neural networks perform brain-inspired computations using photons instead of electrons that can achieve substantially improved computing performance. However, existing architectures can only handle data with regular structures, e.g., images or videos, but fail to generalize to graph-structured data beyond Euclidean space, e.g., social networks or document co-citation networks. Here, we propose an all-optical graph representation learning architecture, termed diffractive graph neural network (DGNN), based on the integrated diffractive photonic computing units (DPUs) to address this limitation. Specifically, DGNN optically encodes node attributes into strip optical waveguides, which are transformed by DPUs and aggregated by on-chip optical couplers to extract their feature representations. Each DPU comprises successive passive layers of metalines to modulate the electromagnetic optical field via diffraction, where the metaline structures are learnable parameters shared across graph nodes. DGNN captures complex dependencies among the node neighborhoods and eliminates the nonlinear transition functions during the light-speed optical message passing over graph structures. We demonstrate the use of DGNN extracted features for node and graph-level classification tasks with benchmark databases and achieve superior performance. Our work opens up a new direction for designing application-specific integrated photonic circuits for high-efficiency processing of large-scale graph data structures using deep learning.
翻译:光学神经网络使用光子而不是能够大幅改进计算性能的电子进行脑动计算。然而,现有的结构只能用常规结构处理数据,例如图像或视频,但不能对超clidean空间以外的图形结构数据进行概括化,例如社交网络或文档共引网络。在这里,我们提议一个全光图代表学习架构,即称为 diffractive 图形神经网络(DGNNN),以综合的diffractive光学计算单位(DPUs)为基础,解决这一限制。具体地说,DGNN光学编码节点属性为条形光学波导线,由DPUs转换,由电动光学对相对等器汇总,以提取其特征图示。每个光学图包含连续的被动金属层,以调整电磁光光光学光学光学场,金属结构是各图形节共用的可学习参数。 DGNNNN在节区之间捕捉到复杂的依赖性关系,并消除非线性转换功能在光学波波波波波波波波波波波波波波波导导导导导结构中,使用高级的高级光电图分析结构,不通过升级的光学分析,不通过新的光学平流平面图图结构,用新平流结构,以完成升级的光序路路路图结构,用新的平流分析,用新的平流路图结构,用新的平流图结构,用新的平流结构,用新的平流图图路路图。