基于真菌网络的动态索引，用更少内存实现更高查询速度。
Mycelium-Index: A Streaming Approximate Nearest Neighbor Index with Myelial Edge Decay, Traffic-Driven Reinforcement, and Adaptive Living Hierarchy
- 模仿真菌生长，通过流量驱动自适应更新索引拓扑。
- 在SIFT-1M上比主流方法少用5.7倍内存，查询速度高4.7倍。
- 适合需要低内存、高吞吐的实时向量搜索场景。
我们提出 mycelium-index，一种面向高维向量空间的流式近似最近邻（ANN）索引，灵感来自生物真菌的自适应生长模式。系统通过菌丝边衰减与强化、流量驱动的动态层级结构，以及结合O(1)绕行冷节点与O(k)束搜索修复枢纽节点的混合删除机制，持续优化拓扑结构。在SIFT-1M上的实验表明，在FreshDiskANN的100%更换率基准下，mycelium在recall@5达到0.927±0.028，与FreshDiskANN约0.95的水平在置信区间内相当，但仅需88 MB内存（低于500 MB），且查询吞吐达2,795 QPS（高于约600）。在静态索引中，ef=192时，mycelium以163 MB内存（相比HNSW M=16的854 MB）达成0.962的召回率，接近其0.965。性能优化包括NEON SIMD距离计算、向量存储节点和位集访问标记，累计提升2.7倍查询速度。对十种流式修复机制的系统研究发现，几何启发式在高维中普遍失效，而拓扑机制表现良好——我们称之为高维ANN图的拓扑修复不变性。
原文摘要 · Abstract (English)
We present mycelium-index, a streaming approximate nearest neighbor (ANN) index for high-dimensional vector spaces, inspired by the adaptive growth patterns of biological mycelium. The system continuously adapts its topology through myelial edge decay and reinforcement, a traffic-driven living hierarchy, and hybrid deletion combining O(1) bypass for cold nodes with O(k) beam-search repair for hub nodes. Experimental evaluation on SIFT-1M demonstrates that mycelium achieves 0.927 +/- 0.028 recall@5 under FreshDiskANN's 100%-turnover benchmark protocol -- within the measurement confidence interval of FreshDiskANN's ~0.95 -- while using 5.7x less RAM (88 MB vs. >500 MB) and achieving 4.7x higher QPS (2,795 vs. ~600). On the static index, at ef=192, mycelium matches HNSW M=16 recall (0.962 vs. 0.965) at 5.2x less RAM (163 MB vs. 854 MB). Performance optimizations including NEON SIMD distance computation, Vec-backed node storage, and bitset visited tracking yield a cumulative 2.7x QPS improvement. A systematic study of ten streaming repair mechanisms finds that geometric heuristics universally fail in high dimensions, while topological mechanisms succeed -- a principle we term the topological repair invariance of high-dimensional ANN graphs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。