将双曲嵌入融入欧式向量索引，提升生物医学本体检索的层次感知能力。
HyEm: Query-Adaptive Hyperbolic Retrieval for Biomedical Ontologies via Euclidean Vector Indexing
- 通过半径控制的双曲嵌入+欧式数据库存储，实现层次结构建模与现有系统兼容
- 在实体查询上保持94-98%基准性能，层次导航与混合意图查询显著提升
- 查询自适应门控动态融合语义与层级信息，适合医疗知识增强生成场景
生物医学知识的检索增强生成面临层次感知的本体对齐挑战：如HPO、DO、MeSH等资源使用深层的'is-a'分类体系，但生产环境依赖欧式嵌入与近似最近邻索引。虽然双曲嵌入更适于层次结构表示，却存在两大障碍：(i) 缺乏原生向量数据库支持，(ii) 在以实体为中心的查询中表现不佳，因层级无关。本文提出HyEm，一种轻量级检索层，将双曲本体嵌入集成至现有欧式近似最近邻基础设施。HyEm学习半径可控的双曲嵌入，将原点对数映射向量存入标准欧式数据库进行候选检索，再进行精确双曲重排序。查询自适应门控输出连续混合权重，在重排序时结合欧式语义相似性与双曲层级距离。基于半李普希茨分析，在半径约束下为近似最近邻过采样和维度提供实用指导。在生物医学本体子集上的实验表明，HyEm在实体相关查询上保留了94-98%的欧式基线性能，同时显著提升层次导航与混合意图查询效果，且在适度过采样下保持索引可扩展性。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) for biomedical knowledge faces a hierarchy-aware ontology grounding challenge: resources like HPO, DO, and MeSH use deep ``is-a" taxonomies, yet production stacks rely on Euclidean embeddings and ANN indexes. While hyperbolic embeddings suit hierarchical representation, they face two barriers: (i) lack of native vector database support, and (ii) risk of underperforming on entity-centric queries where hierarchy is irrelevant. We present HyEm, a lightweight retrieval layer integrating hyperbolic ontology embeddings into existing Euclidean ANN infrastructure. HyEm learns radius-controlled hyperbolic embeddings, stores origin log-mapped vectors in standard Euclidean databases for candidate retrieval, then applies exact hyperbolic reranking. A query-adaptive gate outputs continuous mixing weights, combining Euclidean semantic similarity with hyperbolic hierarchy distance at reranking time. Our bi-Lipschitz analysis under radius constraints provides practical guidance for ANN oversampling and dimensionality.Experiments on biomedical ontology subsets demonstrate HyEm preserves 94-98% of Euclidean baseline performance on entity-centric queries while substantially improving hierarchy-navigation and mixed-intent queries, maintaining indexability at moderate oversampling.
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。