Our work opens up a new direction for designing application-specific integrated photonic circuits for high-efficiency processing large-scale graph data structures using deep learning.ĭeep learning technologies ( 1) have achieved enormous advances in a wide range of artificial intelligence (AI) applications, including computer vision ( 2), speech recognition ( 3), natural language processing ( 4), autonomous vehicles ( 5), biomedical science ( 6), etc. We demonstrate the applications of DGNN for node and graph-level classification tasks with benchmark databases and achieve superior performance. DGNN captures complex dependencies among node neighborhoods during the light-speed optical message passing over graph structures. Specifically, the graph node attributes are encoded into strip optical waveguides, transformed by DPUs, and aggregated by optical couplers to extract their feature representations. Here, we propose the diffractive graph neural network (DGNN), an all-optical graph representation learning architecture based on the diffractive photonic computing units (DPUs) and on-chip optical devices to address this limitation. However, existing architectures can only handle data with regular structures but fail to generalize to graph-structured data beyond Euclidean space. Photonic neural networks perform brain-inspired computations using photons instead of electrons to achieve substantially improved computing performance.
0 Comments
Leave a Reply. |