Fast and Efficient Approximate Nearest Neighbor Search for High-Dimensional LLM Embeddings

[Submitted on 23 Jul 2026]

View PDF HTML (experimental)

Abstract:The annual SISAP Indexing Challenge benchmarks Approximate Nearest Neighbor Search (ANNS) algorithms under rigorous constraints. This paper presents our submissions for the 2026 edition, addressing both $k$-Nearest Neighbor Graph (kNNG) construction on 1024-dimensional BGE-M3 embeddings (Task 1) and Maximum Inner Product Search (MIPS) on unnormalized Llama-3.2-8B features (Task 2). To optimize construction speed, we utilize Equi-Voronoi Polytopes (EVP) for efficient quantization, supplemented by targeted reranking strategies to maintain high recall. For MIPS, we transform the asymmetric inner product problem into a Euclidean search space via dimensionality augmentation. To reduce query latency and optimize memory access, we introduce a 1D presorting mechanism via Fast Linear Assignment Sorting (FLAS) prior to graph construction. This significantly improves spatial locality and cache hit rates during subsequent graph traversal.
Source Code: this https URL

Submission history

From: Nico Hezel [view email]
[v1] Thu, 23 Jul 2026 06:35:12 UTC (199 KB)