Skip to content

Triplet GNN: `compute_loss`, `masked_edges` and new triplet building

Anthony Correia requested to merge anthonyc/gnn_loss_and_triplets into main

This MR introduces

  • Skip batches that go out of memory (for SciFi training)

  • compute_loss argument in common_training_validation_step: only compute the loss when required. For instance, computing the loss in the test sample might require special columns, not available for the latter.

  • masked_edges: a new hparam that allow to mask some edges

  • A refactored triplet building from edges, that separates

    • building triplets from edges
    • computing whether a triplet is fake or genuine

    Allow to compute the truth only if necessary. This is also supposedly faster with less memory consumption.

Edited by Anthony Correia

Merge request reports