Random Node Sampling
Cross-source consensus on Random Node Sampling from 1 sources and 5 claims.
1 sources · 5 claims
Uses
How it works
Benefits
Dosage & preparation
Highlighted claims
- Random Node Sampling partitions all nodes uniformly into approximately equal disjoint subsets at the start of each epoch. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks
- RNS uses the induced subgraph on each subset as a mini-batch and computes loss only for training nodes inside that batch. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks
- RNS has one principal sampling hyperparameter, the number of parts m. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks
- RNS reduces memory and runtime while often matching or improving full-graph test accuracy. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks
- RNS is presented as a strong default baseline for scalable transductive GNN training. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks