EHI: End-to-end Learning Of Hierarchical Index For Efficient Dense Retrieval

Abstract

Dense embedding-based retrieval is widely used for semantic search and ranking. However, conventional two-stage approaches, involving contrastive embedding learning followed by approximate nearest neighbor search (ANNS), can suffer from misalignment between these stages. This mismatch degrades retrieval performance. We propose End-to-end Hierarchical Indexing (EHI), a novel method that directly addresses this issue by jointly optimizing embedding generation and ANNS structure. EHI leverages a dual encoder for embedding queries and documents while simultaneously learning an inverted file index (IVF)-style tree structure. To facilitate the effective learning of this discrete structure, EHI introduces dense path embeddings that encodes the path traversed by queries and documents within the tree. Extensive evaluations on standard benchmarks, including MS MARCO (Dev set) and TREC DL19, demonstrate EHI's superiority over traditional ANNS index. Under the same computational constraints, EHI o

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykumar2023ehi

Related papers

• Hybrid Inverted Index Is A Robust Accelerator For Dense Retrieval (2022)7.07
• Hierarchical Corpus Encoder: Fusing Generative Retrieval And Dense Indices (2025)0.00
• Constructing Tree-based Index For Efficient And Effective Dense Retrieval (2023)9.23
• LIDER: An Efficient High-dimensional Learned Index For Large-scale Dense Passage Retrieval (2022)0.00
• Efficient Neural Ranking Using Forward Indexes And Lightweight Encoders (2023)5.24
• Progressively Optimized Bi-granular Document Representation For Scalable Embedding Based Retrieval (2022)11.06
• End-to-end Retrieval With Learned Dense And Sparse Representations Using Lucene (2023)0.00
• Scaling Laws For Embedding Dimension In Information Retrieval (2026)0.00