Metraipolis › archive › dc_ff934d9cab2c
Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval — arXiv:2608.22980
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22980
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:45:08.450Z
- SHA-256 of the archived text
247613859cc00d404b85eefeb7cdc6ac4a6901bbec24faa10ebbcb4891694fcc- Stable URL of this page
https://metraipolis.com/documento/dc_ff934d9cab2c
How to cite
Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval — arXiv:2608.22980 — arXiv (en), https://arxiv.org/abs/2608.22980 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff934d9cab2c (Metraipolis archive dc_ff934d9cab2c, sha256 247613859cc00d404b85eefeb7cdc6ac4a6901bbec24faa10ebbcb4891694fcc)
BibTeX
@misc{dcff934d9cab2c,
title = {Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval — arXiv:2608.22980},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22980},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff934d9cab2c; sha256 247613859cc00d404b85eefeb7cdc6ac4a6901bbec24faa10ebbcb4891694fcc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22980. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dense vector retrieval has become the foundation of modern semantic search, yet existing approximate nearest neighbor (ANN) indexes treat an embedding as an indivisible point in a high-dimensional space. In this work, we propose the Hypergraph Embedding Index (HEI), a framework that instead organizes documents according to combinations of highly activated latent embedding dimensions. This formulation enables inverted-index style candidate generation while preserving the semantic ranking capabilities of dense embeddings. We further demonstrate that constructing multiple complementary hypergraphs substantially improves retrieval coverage without the combinatorial growth associated with increasing the dimensionality of a single hypergraph. Finally, we establish that the statistical properties of embedding activations strongly influence coordinate-inverted indexing efficiency, introducing \emph{activation diversity} as a diagnostic metric governing embedding indexability in coordinate-inverted frameworks.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.22980 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T07:37:52.910Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).