Lossless compression of vector IDs in IVF and graph indexes, using random-order and random-edge coding plus wavelet trees, reduces ID storage by up to 7x and total index size by 30% at billion scale.
Revisiting the inverted indices for billion-scale approx- imate nearest neighbors
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search
Lossless compression of vector IDs in IVF and graph indexes, using random-order and random-edge coding plus wavelet trees, reduces ID storage by up to 7x and total index size by 30% at billion scale.