StoGCN

2000년 도입 · 논문 1편에서 사용

StoGCN is a control variate based algorithm which allow sampling an arbitrarily small neighbor size. Presents new theoretical guarantee for the algorithms to converge to a local optimum of GCN.

출처: Stochastic Training of Graph Convolutional Networks with Variance Reduction

소개 논문: Stochastic Training of Graph Convolutional Networks with Variance Reduction