BriefGPT.xyz
Mar, 2023
潜在图推断的模型空间投影
Projections of Model Spaces for Latent Graph Inference
HTML
PDF
Haitz Sáez de Ocáriz Borde, Álvaro Arroyo, Ingmar Posner
TL;DR
本文采用超球面和双曲线模型空间的立体投影以及黎曼流形积的方法进行潜在图推理，实现与非投影对应物相当的性能，同时提供理论保证，避免当曲率趋近于零时空间发散的问题，并在同构和异构图上进行了实验。
Abstract
graph neural networks
leverage the connectivity structure of graphs as an inductive bias.
latent graph inference
focuses on learning an adequate graph structure to diffuse information on and improve the downstrea
→