On Efficient Retrieval of Top Similarity Vectors
Retrieval of relevant vectors produced by representation learning critically influences the efficiency in natural language processing (NLP) tasks. In this paper, we demonstrate an efficient method for searching vectors via a typical non-metric matching function: inner product. Our method, which constructs an approximate Inner Product Delaunay Graph (IPDG) for top-1 Maximum Inner Product Search (MIPS), transforms retrieving the most suitable latent vectors into a graph search problem with great benefits of efficiency. Experiments on data representations learned for different machine learning tasks verify the outperforming effectiveness and efficiency of the proposed IPDG.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningRepresentation LearningRetrievalSimilar Papers 제목 키워드 기반
VRSD: Rethinking Similarity and Diversity for Retrieval in Large Language Models
Vector retrieval algorithms are essential for semantic queries within the rapidly evolving landscape of Large Language Models (LLMs). The ability to retrieve vectors that satisfy both similarity and diversity criteria su…
Combinatorial OptimizationDiversityRetrievalCOS-Mix: Cosine Similarity and Distance Fusion for Improved Information Retrieval
This study proposes a novel hybrid retrieval strategy for Retrieval-Augmented Generation (RAG) that integrates cosine similarity and cosine distance measures to improve retrieval performance, particularly for sparse data…
Information RetrievalRAGRetrievalRetrieval-augmented GenerationThe Historical Significance of Textual Distances
Measuring similarity is a basic task in information retrieval, and now often a building-block for more complex arguments about cultural change. But do measures of textual similarity and distance really correspond to evid…
Information RetrievalRetrievalFace Image Retrieval With Attribute Manipulation
Current face image retrieval solutions are limited, since they treat different facial attributes the same and cannot incorporate user's preference for a subset of attributes in their search criteria. This paper intro…
AttributeFace Image RetrievalImage RetrievalRetrievalVectorSearch: Enhancing Document Retrieval with Semantic Embeddings and Optimized Search
Traditional retrieval methods have been essential for assessing document similarity but struggle with capturing semantic nuances. Despite advancements in latent semantic analysis (LSA) and deep learning, achieving compre…
Retrieval