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.
Source: Stochastic Training of Graph Convolutional Networks with Variance ReductionPaper | Code | Results | Date | Stars |
---|
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |