Methods › General › Attention Mechanisms › SortCut Sinkhorn Attention
SortCut Sinkhorn Attention
Introduced by Yi Tay et al. in Sparse Sinkhorn Attention
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SortCut Sinkhorn Attention is a variant of Sparse Sinkhorn Attention where a post-sorting truncation of the input sequence is performed, essentially performing a hard top-k operation on the input sequence blocks within the computational graph. While most attention models mainly re-weight or assign near-zero weights during training, this allows for explicitly and dynamically truncate the input sequence. Specifically:
Y = Softmax(Qψ_S(K)ᵀ_([:n]))ψ_S(V)_([:n])
where n is the Sortfut budget hyperparameter.
Papers archive 2025-07-28
1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Sparse Sinkhorn Attention 26 Feb 2020 · 1 repository · arXiv:2002.11296
Tasks archive 2025-07-28
5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Document Classification | 1 |
| Image Generation | 1 |
| Language Modeling | 1 |
| Language Modelling | 1 |
| Natural Language Inference | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections