SelfAdversarialLoss

class ampligraph.latent_features.SelfAdversarialLoss(eta, hyperparam_dict={'alpha': 0.5, 'margin': 3}, verbose=False)

Self adversarial sampling loss.

Introduced in [SDNT19].

\[\mathcal{L} = -log \sigma(\gamma - d_r (h,t)) - \sum_{i=1}^{n} p(h_{i}^{'}, r, t_{i}^{'} ) \ log \ \sigma(d_r (h_{i}^{'},t_{i}^{'}) - \gamma)\]

where \(\gamma\) is the margin, and \(p(h_{i}^{'}, r, t_{i}^{'} )\) is the sampling proportion

Methods

__init__(eta[, hyperparam_dict, verbose])

Initialize Loss

__init__(eta, hyperparam_dict={'alpha': 0.5, 'margin': 3}, verbose=False)

Initialize Loss

Parameters:

• eta (int) – number of negatives
• hyperparam_dict (dict) –

  dictionary of hyperparams.

  • margin: float. Margin to be used in adversarial loss computation (default:3)
  • alpha : float. Temperature of sampling (default:0.5)