However, the number of neighboring units is neither fixed nor are they ordered in generic graphs, thereby hindering the applications of convolutional operations. To enable model training on large-scale graphs, we propose a sub-graph training method to reduce the excessive memory and computational resource requirements suffered by prior methods on graph convolutions. Our results also indicate that the proposed methods using sub-graph training strategy are more efficient as compared to prior approaches.
|Task||Dataset||Model||Metric name||Metric value||Global rank||Compare|
|Node Classification||Citeseer||LGCN sub||Accuracy||73.0%||# 1|
|Node Classification||Cora||LGCN sub||Accuracy||83.30%||# 1|
|Node Classification||Pubmed||LGCN sub||Accuracy||79.50%||# 2|