Accurate and Fast Retrieval for Complex Non-metric Data via Neighborhood Graphs
We demonstrate that a graph-based search algorithm-relying on the construction of an approximate neighborhood graph-can directly work with challenging non-metric and/or non-symmetric distances without resorting to metric-space mapping and/or distance symmetrization, which, in turn, lead to substantial performance degradation. Although the straightforward metrization and symmetrization is usually ineffective, we find that constructing an index using a modified, e.g., symmetrized, distance can improve performance. This observation paves a way to a new line of research of designing index-specific graph-construction distance functions.
Code (0)
등록된 구현이 없습니다.
Tasks
graph constructionRetrievalSimilar Papers 제목 키워드 기반
Product Quantization Network for Fast Image Retrieval
Product quantization has been widely used in fast image retrieval due to its effectiveness of coding high-dimensional visual features. By extending the hard assignment to soft assignment, we make it feasible to incorpora…
Image RetrievalQuantizationRetrievalTripletBuild Fast and Accurate Lemmatization for Arabic
In this paper we describe the complexity of building a lemmatizer for Arabic which has a rich and complex derivational morphology, and we discuss the need for a fast and accurate lammatization to enhance Arabic Informati…
Information RetrievalLemmatizationRetrievalFastRAG: Retrieval Augmented Generation for Semi-structured Data
Efficiently processing and interpreting network data is critical for the operation of increasingly complex networks. Recent advances in Large Language Models (LLM) and Retrieval-Augmented Generation (RAG) techniques have…
ManagementQuestion AnsweringRAGRetrieval+1RetrievalRouter: Joint Modality and Architecture Selection for Document Retrieval
Document retrieval increasingly supports high-stakes information access in finance, healthcare, and law. Modern retrieval pipelines vary both in modality (text or multimodal) and in retrieval architecture (dense or late-…
Adaptive additive classification-based loss for deep metric learning
Recent works have shown that deep metric learning algorithms can benefit from weak supervision from another input modality. This additional modality can be incorporated directly into the popular triplet-based loss functi…
ClassificationGeneral ClassificationMetric LearningRetrieval+1