Computes the npairs loss between multilabel data `y_true` and `y_pred`.
loss_npairs_multilabel(name = "npairs_multilabel_loss")
| name | Optional name for the op. |
|---|
npairs_multilabel_loss: float scalar.
Npairs loss expects paired data where a pair is composed of samples from the same labels and each pairs in the minibatch have different labels. The loss takes each row of the pair-wise similarity matrix, `y_pred`, as logits and the remapped multi-class labels, `y_true`, as labels. To deal with multilabel inputs, the count of label intersection is computed as follows: ``` L_i,j = | set_of_labels_for(i) `\cap` set_of_labels_for(j) | ``` Each row of the count based label matrix is further normalized so that each row sums to one. `y_true` should be a binary indicator for classes. That is, if `y_true[i, j] = 1`, then `i`th sample is in `j`th class; if `y_true[i, j] = 0`, then `i`th sample is not in `j`th class. The similarity matrix `y_pred` between two embedding matrices `a` and `b` with shape `[batch_size, hidden_size]` can be computed as follows: ``` # y_pred = a * b^T y_pred = tf.matmul(a, b, transpose_a=FALSE, transpose_b=TRUE) ```
http://www.nec-labs.com/uploads/images/Department-Images/MediaAnalytics/papers/nips16_npairmetriclearning.pdf