Re:Harnessing the Universal Geometry of Embeddings
by jxmorris12 on Wednesday May 21, 2025 @03:57PM
(#44055638)
Yes. So the idea was that an orthogonal rotation will 'encrypt' the embeddings without affecting performance, since orthogonality preserves cosine similarity. It's a good idea, but we can un-rotate the embeddings using our GAN.
Re:Harnessing the Universal Geometry of Embeddings
by srean on Wednesday May 21, 2025 @04:00PM
(#44055675)
I can understand that relatively rotated embeddings from the same or similar dataset can be realigned. The same way we can re-align two globes -- look for matching shapes.
That essentially would be akin to solving a graph isomorphism problem.
Lie algebraic formulation would make it less generic than an arbitrary graph-isomorphism problem. Essentially reduce it to a high dimensional procrustes problem. Generic graph isomorphism can be quite a challenge.
Re:Harnessing the Universal Geometry of Embeddings
by jxmorris12 on Wednesday May 21, 2025 @04:04PM
(#44055714)
Right, that's why the baselines here come from the land of Optimal Transport, which looks at the world through isomorphisms, exactly as you've suggested.
The GAN works way better than traditional OT methods though. I really don't know why, this is the part that feels like magic to me.
Re:Harnessing the Universal Geometry of Embeddings
by srean on Wednesday May 21, 2025 @04:09PM
(#44055769)
Got you. I can understand that this has a chance of working if the embeddings have converted to their global optimum. Otherwise all bets ought to be off.
All the best.
I can totally understand the professors point, little bit of alignment data ought significantly increase the chance of success. Otherwise it will have to rely on these small deviations from symmetry to anchor the orientation.
Re:Harnessing the Universal Geometry of Embeddings
by jxmorris12 on Wednesday May 21, 2025 @04:16PM
(#44055850)
Yeah, we didn't get around to testing what the impact would be of having a small amount of aligned data. I've seen other papers asserting that as few as five pairs is enough to go a long way.
For example, global rotation that does not change embedded vector x embedded vector dot-product and changes query vector x embedded dot-product in an equivariant way.