In high-dimensional data processing,the K-nearest neighbor(KNN)graph is a critical data structure widely used in tasks such as clustering,graph neural networks,and recommendation systems.However,with the increasing use of pretrained embedding models in unstructured data modeling and retrieval,embedding model fine-tuning has become a key step in enhancing the semantic representation capability of embeddings.Such fine-tuning often leads to systematic changes in the vector representations of all data points,which invalidates the original neighborhood relationships in the KNN graph.Existing research primarily focuses on building KNN graphs for static data,lacking efficient solutions for adapting to updated embeddings after fine-tuning.To address this gap,this study proposes FastAdjust,an efficient KNN graph update method tailored for embedding model fine-tuning scenarios.Leveraging the observation that fine-tuning usually causes only minor changes to individual embeddings,incremental adjustments to the original KNN graph are performed by FastAdjust through a local update strategy,significantly improving update efficiency while maintaining graph quality.Specifically,FastAdjust first employs a clustering structure based on product quantization to efficiently and accurately locate a subset of candidate neighbors for each data point,thus narrowing the search space.Secondly,based on data density and the magnitude of embedding variation,FastAdjust leverages their correlation with changes in the KNNs to adaptively allocate update resources according to the degree of neighbor relationship changes,thus improving overall update efficiency.Experimental results on real-world datasets demonstrate that FastAdjust efficiently and accurately adapts KNN graphs to embedding updates with significantly reduced computational cost,showing strong practical value and scalability.
With the widespread application of multi-source,heterogeneous,and multi-modal data in scenarios such as large models and data lakes,there has been a significant growth in vector-based data retrieval and storage management.By mapping heterogeneous data into high-dimensional vector representations and leveraging vector indices,vector databases facilitate the unified management of diverse data types and enable high-quality similarity search,establishing them as a crucial foundation for applications like generative retrieval and AI-native databases.However,existing vector databases face significant bottlenecks in terms of storage and indexing efficiency,index construction complexity,and retrieval accuracy.Specifically,massive high-dimensional vectors lead to increased storage overhead and maintenance costs for indices.Furthermore,vector index structures are often bloated,resulting in substantial memory consumption.Moreover,the degradation of retrieval accuracy caused by distortion from compression techniques remains an unresolved challenge.This study proposes a framework based on weight residual vector quantization(WRVQ).This method achieves efficient compression and storage with very low distortion by decoupling the quantization direction from the residual magnitude.It stores the residual direction as a unit vector and appends a weight marker.For indexing,a three-layer inverted index structure tailored to the characteristics of WRVQ is designed,comprising an exact match layer,a fuzzy match layer,and a search layer.This structure organically integrates asymmetric distance computation(ADC)with nearest neighbor search techniques to realize approximate nearest neighbor(ANN)search that balances both high accuracy and high efficiency.Experimental results on large-scale datasets demonstrate that,compared to traditional low-dimensional embedding models and existing quantization methods,WRVQ achieves significant improvements across key metrics,including quantization loss,storage compression ratio,and retrieval recall.Furthermore,it exhibits considerable advantages in both index construction and query performance.
Text2SQL has evolved into a significant tool for data analysis and database management by reducing the technical barriers for non-expert users to interact with relational databases.The introduction of large language model(LLM),represented by GPT,further improves the performance of Text2SQL systems.However,existing Text2SQL techniques are difficult to apply directly to the spatial database domain because spatial data involves complex geometric relationships,diverse query types,and the demand for high-precision semantic understanding.To address these issues and lower the threshold for interaction between non-experts and spatial databases,a natural language query(NLQ)transformation method for spatial databases is proposed.The method consists of two core phases:(1)natural language understanding;(2)executable language generation.In phase(1),an entity information extraction algorithm is employed to extract key query entities,and a spatial data query corpus is constructed based on large language models to determine the query type.In phase(2),a structured language model(SLM)is selected according to the query type,and the entities are then mapped into the structured language model to generate the final executable language for spatial databases.Experimental results on multiple real-world datasets demonstrate that the proposed method enables efficient transformation from natural language queries to executable languages of spatial databases.
Graph-based high-dimensional vector indices have become a mainstream solution for large-scale approximate nearest neighbor search (ANNS). However, their substantial memory footprint often requires storage on secondary devices, where frequent on-demand loading of graph and vector data leads to I/O becoming the dominant bottleneck, accounting for over 90% of query latency. Existing static caching strategies mitigate this issue only in the initial navigation phase by preloading entry points and multi-hop neighbors, but they fail in the second phase where query-dependent nodes must be dynamically accessed to achieve high recall. We propose GoVector, an I/O-efficient caching strategy tailored for disk-based graph indices. GoVector combines (1) a static cache that stores entry points and frequently accessed neighbors, and (2) a dynamic cache that adaptively captures nodes with high spatial locality during the second search phase. To further align storage layout with similarity-driven search patterns, GoVector reorders nodes on disk so that similar vectors are colocated on the same or adjacent pages, thereby improving locality and reducing I/O overhead. Extensive experiments on multiple public datasets show that GoVector achieves substantial performance improvements. At 90
In certain designs and applications of practical lattice-based cryptography,the use of a specialized variant of LWE problems,where the public matrix is sampled from a non-uniform distribution,is required to establish the securities of corresponding cryptographic schemes.Recently,the formal definition of LWE problems with semi-uniform seeds was introduced in some work,in which the hardness of Euclidean,ideal,and module lattice-based LWE problems with semi-uniform seeds was proved through reduction roadmaps similar to those employed in the hardness proofs of entropic LWE problems.However,known reduction introduces significant losses in the Gaussian parameters of errors and dimensions.Moreover,additional non-standard assumptions are required to demonstrate the hardness of LWE problems with semi-uniform seeds over rings.In this study,a tighter reduction is proposed for LWE problems with semi-uniform seeds by incorporating modified techniques from the hardness proofs of Hint-LWE problems.The proposed reduction is largely unaffected by the algebraic structures of the underlying problems and can be uniformly applied to Euclidean,ideal,and module lattice-based LWE problems with semi-uniform seeds.The hardness of these LWE problems can be established based on standard LWE assumptions without the need for any additional non-standard assumptions.Furthermore,the dimension of the corresponding LWE problems remains unchanged,and the reduction introduces only minimal losses in Gaussian parameters of errors.
