Mini-batch GNN Training
Cross-source consensus on Mini-batch GNN Training from 1 sources and 4 claims.
1 sources · 4 claims
How it works
Comparisons
Highlighted claims
- Mini-batch training for GNNs changes the topology available to the model by removing edges that cross the batch boundary. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks
- Graph mini-batching should be understood as changing the training objective rather than merely approximating full-graph training. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks
- Sampler choice affects the effective objective through both sampled-loss bias and mini-batch gradient variance. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks
- Subgraph mini-batch training computes the supervised loss only on training nodes inside the sampled subgraph. — Implicit Regularization of Mini-Batch Training in Graph Neural Networks