Hybrid Indexes by Exploring Traditional B-Tree and Linear Regression

Qu, Wenwen; Wang, Xiaoling; Li, Jingdong; Li, Xin

doi:10.1007/978-3-030-30952-7_61

Cited by 8 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ASLM [34] partitions data with the maximum intervals, and uses cache as a transfer for updates. Hybrid-LR [35] stores outliers separately in B-tree to stabilize model accuracy. FITing-tree [36] reserves extra physical space for each partition.…”

Section: Learned Indicesmentioning

confidence: 99%

SLBRIN: A Spatial Learned Index Based on BRIN

Wang

et al. 2023

IJGI

View full text Add to dashboard Cite

The spatial learned index constructs a spatial index by learning the spatial distribution, which performs a lower cost of storage and query than the spatial indices. The current update strategies of spatial learned indices can only solve limited updates at the cost of query performance. We propose a novel spatial learned index structure based on a Block Range Index (SLBRIN for short). Its core idea is to cooperate history range and current range to satisfy a fast spatial query and efficient index update simultaneously. SLBRIN deconstructs the update transaction into three parallel operations and optimizes them based on the temporal proximity of spatial distribution. SLBRIN also provides the spatial query strategy with the spatial learned index and spatial location code, including point query, range query and kNN query. Experiments on synthetic and real datasets demonstrate that SLBRIN clearly outperforms traditional spatial indices and state-of-the-art spatial learned indices in the cost of storage and query. Moreover, in the simulated real-time update scenario, SLBRIN has the faster and more stable query performance while satisfying efficient updates.

show abstract

Section: Learned Indicesmentioning

confidence: 99%

SLBRIN: A Spatial Learned Index Based on BRIN

Wang

et al. 2023

IJGI

View full text Add to dashboard Cite

show abstract

“…Apart from Parliament [45], one can rarely find data representations supporting traversal patterns as required by k-hop and *-hop access patterns. Furthermore, solutions tend to rely on standard B+-tree and hash map implementations, avoiding the use of hybrid structures (e.g., hybrid indexes [65]). An exception is the VS*-tree adopted by gStore [88], which, among others, can also return all subjects or objects that match a specific set of predicates and values, thus addressing the needs of a subset of the N-way pivot access pattern where the variable has the same position in all triple patterns.…”

Section: A Compatibility-based Analysismentioning

confidence: 99%

A design space for RDF data representations

et al. 2022

View full text Add to dashboard Cite

RDF triplestores’ ability to store and query knowledge bases augmented with semantic annotations has attracted the attention of both research and industry. A multitude of systems offer varying data representation and indexing schemes. However, as recently shown for designing data structures, many design choices are biased by outdated considerations and may not result in the most efficient data representation for a given query workload. To overcome this limitation, we identify a novel three-dimensional design space. Within this design space, we map the trade-offs between different RDF data representations employed as part of an RDF triplestore and identify unexplored solutions. We complement the review with an empirical evaluation of ten standard SPARQL benchmarks to examine the prevalence of these access patterns in synthetic and real query workloads. We find some access patterns, to be both prevalent in the workloads and under-supported by existing triplestores. This shows the capabilities of our model to be used by RDF store designers to reason about different design choices and allow a (possibly artificially intelligent) designer to evaluate the fit between a given system design and a query workload.

show abstract

“…Instead, the position of a key after correction depends on both 𝑁 𝐹 𝜃 (𝑥) (prediction) and 𝑀𝐹 𝜃 (𝑥) (partition number). For example, all keys belonging to 𝑃 30 23 , i.e., data [35 The drift of 𝑃 𝑀 𝑘 , namely Δ𝑀 𝑘 is the index of the median key among the members of 𝑃 𝑀 𝑘 . This means that if the key is predicted to be in the 𝑘'th partition (among the 𝑀 partitions), the local search is done around [𝑁 𝐹 𝜃 (𝑥)] + Δ𝑀 𝑘 .…”

Section: Compressing the Shift-table Layermentioning

confidence: 99%

“…Also, numerous efforts have been made to handle practical challenges around using a learned index, including updatehandling [7,16] and designing a learned DBMS [23]. The idea of using a model of the data to boost an existing algorithmic index has been the center of focus in the past few years [14,16,18,35]. In the multivariate area, learning from a sample workload has also shown interesting results [8,19,27,31].…”

Section: Related Workmentioning

confidence: 99%

Shift-Table: A Low-latency Learned Index for Range Queries using Model Correction

Hadian,

Heinis

2021

Preprint

View full text Add to dashboard Cite

Indexing large-scale databases in main memory is still challenging today. Learned index structures -in which the core components of classical indexes are replaced with machine learning models -have recently been suggested to significantly improve performance for read-only range queries.However, a recent benchmark study shows that learned indexes only achieve limited performance improvements for realworld data on modern hardware. More specifically, a learned model cannot learn the micro-level details and fluctuations of data distributions thus resulting in poor accuracy; or it can fit to the data distribution at the cost of training a big model whose parameters cannot fit into cache. As a consequence, querying a learned index on real-world data takes a substantial number of memory lookups, thereby degrading performance.In this paper, we adopt a different approach for modeling a data distribution that complements the model fitting approach of learned indexes. We propose Shift-Table , an algorithmic layer that captures the micro-level data distribution and resolves the local biases of a learned model at the cost of at most one memory lookup. Our suggested model combines the low latency of lookup tables with learned indexes and enables low-latency processing of range queries. Using Shift-Table, we achieve a speedup of 1.5X to 2X on real-world datasets compared to trained and tuned learned indexes.

show abstract

Hybrid Indexes by Exploring Traditional B-Tree and Linear Regression

Cited by 8 publications

References 16 publications

SLBRIN: A Spatial Learned Index Based on BRIN

SLBRIN: A Spatial Learned Index Based on BRIN

A design space for RDF data representations

Shift-Table: A Low-latency Learned Index for Range Queries using Model Correction

Contact Info

Product

Resources

About