AI 中文总结
本文针对2026年SISAP索引挑战赛，介绍在高维语言模型嵌入上的近似最近邻搜索方法。利用EVP量化、重排策略及维度扩充等优化算法，通过FLAS预排序机制减少查询延迟和优化内存访问，提升空间局部性与缓存命中率。
AI 中文摘要
年度SISAP索引挑战赛在严格约束下对近似最近邻搜索（ANNS）算法进行基准测试。本文展示了我们在2026年版本中的提交内容，涉及在1024维BGE - M3嵌入上构建k近邻图（任务1）以及对未归一化的Llama - 3.2 - 8B特征进行最大内积搜索（任务2）。为优化构建速度，利用等距Voronoi多面体（EVP）进行高效量化，并辅以目标重排策略以保持高召回率。对于MIPS，通过维度扩充将不对称内积问题转化为欧几里得搜索空间。为减少查询延迟并优化内存访问，在图构建前通过快速线性分配排序（FLAS）引入一维预排序机制，显著提高了后续图遍历中的空间局部性和缓存命中率。
英文摘要
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: https://github.com/Visual-Computing/sisap26-deglib
