NLLLoss

class ampligraph.latent_features.NLLLoss(eta, hyperparam_dict={}, verbose=False)

Negative log-likelihood loss.

As described in [TWR+16].

\[\mathcal{L}(\Theta) = \sum_{t \in \mathcal{G} \cup \mathcal{C}}log(1 + exp(-yf_{model}(t;\Theta)))\]

where \(y\) is the label of the statement :math:` in [-1, 1]`, \(\mathcal{G}\) is the set of positives, \(\mathcal{C}\) is the set of corruptions, \(f_{model}(t;\Theta)\) is the model-specific scoring function.

Methods

__init__(eta[, hyperparam_dict, verbose])

Initialize Loss.

__init__(eta, hyperparam_dict={}, verbose=False)

Initialize Loss.

Parameters:

• eta (int) – number of negatives
• hyperparam_dict (dict) – dictionary of hyperparams. No hyperparameters are required for this loss.