This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
attention [2018/10/02 19:56]
attention [2018/10/02 19:57] (current)
Line 308: Line 308:
 https://​openreview.net/​forum?​id=rJxHsjRqFQ Hyperbolic Attention Networks ​ https://​openreview.net/​forum?​id=rJxHsjRqFQ Hyperbolic Attention Networks ​
 +By only changing the geometry of embedding of object representations,​ we can use the embedding space more efficiently without increasing the number of parameters of the model. Mainly as the number of objects grows exponentially for any semantic distance from the query, hyperbolic geometry ​ --as opposed to Euclidean geometry-- can encode those objects without having any interference. Our method shows improvements in generalization on neural machine translation on WMT'14 (English to German), learning on graphs (both on synthetic and real-world graph tasks) and visual question answering (CLEVR) tasks while keeping the neural representations compact.