UniPROT reformulates uniform prototype selection as a partial optimal transport problem that yields a submodular objective admitting a greedy algorithm with (1-1/e) approximation guarantee.
However, these approaches typicallylearn synthetic samplesor optimize continuous representations, rather than selecting a subset from a given discrete pool
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees
UniPROT reformulates uniform prototype selection as a partial optimal transport problem that yields a submodular objective admitting a greedy algorithm with (1-1/e) approximation guarantee.