Training ideas

Curricula, sampling schedules, pseudo-labeling and multi-task mixing, with the standard training recipe as the control.

2 ideas found

Category: Training ML: Graph nn Math: Linear algebra Clear all

✓✓ Beats tuned baseline 2026

Laplacian-Coherence Graph Minibatches

Replace uniform node minibatches in a GNN with a coreset selected from a small random candidate set using local Laplacian-column coherence. Select nodes whose connectivity signatures are least redundant with already selected nodes, while retaining inverse-probability weights for unbiased loss estimates. This should improve coverage of weakly connected graph clusters and preserve smooth graph signals at the same batch size.

Useful7/10

Difficulty5/10

Novelty7/10

Training Sample efficiency Scalability Accuracy

Paper: Scalable Graph Coreset Selection via Greedy Sampling arXiv:2607.27602

Unverified 2026

Stiffness-energy supervision without FEM labels

Train a finite-element surrogate by minimizing the assembled discrete potential energy rather than a loss against solved displacement labels. The objective uses only the sparse stiffness matrix and load vector, while its exact energy-gap identity makes it equivalent to supervised regression in the stiffness norm.

Useful6/10

Difficulty3/10

Novelty5/10

Training Sample efficiency Speedup Accuracy

Paper: Discrete energy as an exact label-free training objective for finite-element surrogates arXiv:2608.05437