method
active
method:l-stochastic-recon-loss

L_stochastic-recon loss

Loss on randomly masked subcomponents matching target outputs, with layerwise auxiliary.

Neighborhood — ranked by edge-count

Papers (1)

paper

Frameworks (1)

framework

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • L_retain Loss Termconcept0.738
    Regularization component of the composite loss that penalizes deviation from baseline model behavior on Alpaca instructions
  • Samples task weights from a standard normal distribution.
  • Penalizes causal importance values above 0 with p-norm; works with p>1.
  • Loss Recoveredmethod0.719
    Reconstruction fidelity score based on cross-entropy.
  • Transformers are recurrent through autoregression because the K/V stream provides horizontal information flow across positions, even though each forward pass is feedforward.
  • Distance-based loss comparing injected representation to class centroids in the active subspace
  • Auxiliary training objective from Grant (2025) that constrains intervened representations to remain near natural distribution
  • Auxiliary objective combining L2 and cosine losses against pre-recorded CL vectors to improve causal relevance when one model is causally inaccessible.