🪛🔗 Change interactions' shape

[mberr]

This PR is a draft to change the format from the "more canonical" shape (batch_size, num_heads, num_relations, num_tails, *dims) to an arbitrary number of batch dimensions (*batch_dims, *dims), This should avoid some of the unnecessary dimension expansion and reductions, which may be the cause of the performance issue observed in #735 .

In particular it allows score_hrt from shape (batch_size, dim) instead of the expansion to (batch_size, 1, 1, 1, dim).

[mberr]

Should this PR should also retire the following:

* [x]  `pykeen.nn.emb.RepresentationModule.get_in_more_canonical_shape` (now unused - done in [aa557ec](https://github.com/pykeen/pykeen/commit/aa557ece88b43a08b0e006c465ba356b8755d854))

* [ ]  `pykeen.nn.emb.RepresentationModule.get_in_canonical_shape` (still used in a few places)

part 2 depends on moving the users of this method to new-style, which may require a re-check of performance implications.

Opened a new issue in #739

[mberr]

I verified that the BoxE repro config on WN18RR still succeeds.

[mberr]

@PyKEEN-bot test

[cthoyt]

either look into changing the score_hrt()/self() dichotomy, or just