← 피드로
[Submitted on 24 Aug 2026]
Abstract: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.
Submission history
From: Kishore Konda Dr [view email]
[v1]
Mon, 24 Aug 2026 08:40:17 UTC (15 KB)
추출 본문 · 출처: arxiv.org · https://arxiv.org/abs/2608.22980