An official website of the United States government
Abstract In this work, we explore multiplex graph (networks with different types of edges) generation with deep generative models. We discuss some of the challenges associated with multiplex graph generation that make it a more difficult problem than traditional graph generation. We propose TenGAN, the first neural network for multiplex graph generation, which greatly reduces the number of parameters required for multiplex graph generation. We also propose 3 different criteria for evaluating the quality of generated graphs: a graph-attribute-based, a classifier-based, and a tensor-based method. We evaluate its performance on 4 datasets and show that it generally performs better than other existing statistical multiplex graph generative models. We also adapt HGEN, an existing deep generative model for heterogeneous information networks, to work for multiplex graphs and show that our method generally performs better.
more »
« less
Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to non-federal websites. Their policies may differ from this site.
-
-
The design, fabrication, and characterization of a 16-element optical phased array (OPA) using a high index (n = 3.1) silicon-rich silicon nitride (SRN) is demonstrated. We present one-dimensional beam steering with end-fire facet antennas over a wide steering range of >115° at a fixed wavelength of 1525 nm. A beam width of 6.3° has been measured at boresight, consistent with theory. We demonstrate SRN as a viable material choice for chip-scale OPA applications due to its high thermo-optic coefficient, high optical power handling capacity [negligible two-photon absorption (TPA)], wide transparency window, and CMOS compatibility.more » « less
-
The design, fabrication, and characterization of low-loss ultra-compact bends in high-index ( at ) plasma-enhanced chemical vapor deposition silicon-rich silicon nitride (SRN) were demonstrated and utilized to realize efficient, small footprint thermo-optic phase shifter. Compact bends were structured into a folded waveguide geometry to form a rectangular spiral within an area of , having a total active waveguide length of 1.2 mm. The device featured a phase-shifting efficiency of and a 3 dB switching bandwidth of 15 KHz. We propose SRN as a promising thermo-optic platform that combines the properties of silicon and stoichiometric silicon nitride.more » « less
Full Text Available