Structure-aware Samplers

Cross-source consensus on Structure-aware Samplers from 1 sources and 5 claims.

1 sources · 5 claims

Uses

RNS achieves the best test accuracy among the evaluated mini-batch methods on OGBN-ARXIV, OGBN-PRODUCTS, and POKEC. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks
The sampler comparison evaluates Neighborhood Sampling, ClusterGCN, GraphSAINT, LADIES, RNS, and full-graph training on three main datasets. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks
The RNS node-subsampling bias argument does not apply to ClusterGCN or GraphSAINT because their sampled target sets are not conditionally uniform over training nodes. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks
Prior scalable GNN methods often use structure-aware samplers to preserve local connectivity or reduce embedding variance. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks
Structure-aware samplers may create batches that differ systematically from one another and lead to larger per-batch gradient variance. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks