tf.compat.v1.nn.sampled_softmax_loss

Computes and returns the sampled softmax training loss.

tf.compat.v1.nn.sampled_softmax_loss(
    weights, biases, labels, inputs, num_sampled, num_classes, num_true=1,
    sampled_values=None, remove_accidental_hits=True, partition_strategy='mod',
    name='sampled_softmax_loss', seed=None
)

This is a faster way to train a softmax classifier over a huge number of classes.

This operation is for training only. It is generally an underestimate of the full softmax loss.

A common use case is to use this method for training, and calculate the full softmax loss for evaluation or inference. In this case, you must set partition_strategy="div" for the two losses to be consistent, as in the following example:

if mode == "train":
  loss = tf.nn.sampled_softmax_loss(
      weights=weights,
      biases=biases,
      labels=labels,
      inputs=inputs,
      ...,
      partition_strategy="div")
elif mode == "eval":
  logits = tf.matmul(inputs, tf.transpose(weights))
  logits = tf.nn.bias_add(logits, biases)
  labels_one_hot = tf.one_hot(labels, n_classes)
  loss = tf.nn.softmax_cross_entropy_with_logits(
      labels=labels_one_hot,
      logits=logits)

See our Candidate Sampling Algorithms Reference (pdf). Also see Section 3 of (Jean et al., 2014) for the math.

References:

On Using Very Large Target Vocabulary for Neural Machine Translation: Jean et al., 2014 (pdf)