Hyem: Query-adaptive Hyperbolic Retrieval For Biomedical Ontologies Via Euclidean Vector Indexing
2026 Β· Ou Deng, Shoji Nishimura, Atsushi Ogihara, et al.
Abstract
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 pract
Authors
(none)
Tags
Stats
Related papers
- Hyprag: Hyperbolic Dense Retrieval For Retrieval Augmented Generation (2026)0.00
- EHI: End-to-end Learning Of Hierarchical Index For Efficient Dense Retrieval (2023)0.00
- Hypencoder: Hypernetworks For Information Retrieval (2025)4.52
- Self-aware Vector Embeddings For Retrieval-augmented Generation: A Neuroscience-inspired Framework For Temporal, Confidence-weighted, And Relational Knowledge (2026)0.00
- Hierarchical Retrieval: The Geometry And A Pretrain-finetune Recipe (2025)0.99
- Treehop: Generate And Filter Next Query Embeddings Efficiently For Multi-hop Question Answering (2025)2.98
- Multimodal RAG For Unstructured Data:leveraging Modality-aware Knowledge Graphs With Hybrid Retrieval (2025)0.00
- Hyqe: Ranking Contexts With Hypothetical Query Embeddings (2024)5.74