PCA-based static dimension pruning of dense document embeddings reduces storage and latency by about half with under 5% NDCG@10 loss on MS MARCO and BEIR COVID.
Dumais, George W
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Static Pruning in Dense Retrieval using Matrix Decomposition
PCA-based static dimension pruning of dense document embeddings reduces storage and latency by about half with under 5% NDCG@10 loss on MS MARCO and BEIR COVID.