CompresSAE, a sparse autoencoder with cosine reconstruction loss, compresses dense embeddings 12x with a small retrieval quality drop and beats same-size Matryoshka embeddings online.
Title resolution pending
1 Pith paper cite this work, alongside 305 external citations. Polarity classification is still indexing.
1
Pith paper citing it
305
external citations · OpenAlex
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Future is Sparse: Embedding Compression for Scalable Retrieval in Recommender Systems
CompresSAE, a sparse autoencoder with cosine reconstruction loss, compresses dense embeddings 12x with a small retrieval quality drop and beats same-size Matryoshka embeddings online.