Add Relation that works with negative edge sampling

[einbandi]

The relations that exist so far all calculate square matrices Rel(x_i, x_j) with x_i and x_j in X. For negative edge sampling, a batch consists of row (row) and column (col) indices, so only Rel(x_row[i], y_col[i]) for i from 0 to len(row) - 1 must be calculated. For a single item, len(row) = neg_sampling_rate + 1. I don't want to calculate the full matrix and subsample, as this is inefficient.

[einbandi]

A quick solution would be to implement DistsFromTo, whose compute_relations method takes a tensor of shape (2, n, dim) and returns a list of n distances in the form of a new RelationData subclass (e.g., RelationTensor and/or RelationArray) without any conversion methods.

[einbandi]

If this is the only relation that works with negative edge sampling, is there a way to set it by default so it doesn't have to be specified? What about the sub methods that should be implemented for all other relations?