Topology Generation
Topology generation focuses on creating and manipulating graph structures, addressing challenges in diverse fields from circuit design to material science. Current research emphasizes the use of deep learning models, including graph neural networks and diffusion models, to generate realistic and efficient graph representations, often incorporating techniques like information bottleneck principles for robustness and data-driven approaches for improved accuracy. These advancements are impacting various applications, enabling automated circuit design, improved link prediction in networks, and more accurate modeling of complex systems for simulations and analysis.
8papers
Papers
March 13, 2023
Fast exploration and learning of latent graphs with aliased observations
Miguel Lazaro-Gredilla, Ishan Deshpande, Sivaramakrishnan Swaminathan, Meet Dave, Dileep GeorgeDetecting hidden structures from a static loading experiment: topology optimization meets physics-informed neural networks
Saviz Mowlavi, Ken Kamrin