This paper presents an exploration, implementations, and revisions of probabilistic sets and maps, specifically focusing on Bloomier filters and related data structures. The paper introduces the Fuse XORier Lookup Table (FXLT), an enhanced version of the Bloomier Filter incorporating spatial coupling, linear construction, and optimizations. The authors provide implementations in C and Python, comparing the FXLT's performance with other data structures like bloom filters, XOR filters, binary fuse filters, hash tables, and red-black trees. The FXLT demonstrates improvements in both space and time efficiency over traditional Bloomier Filters and appears competitive with hash tables for large datasets.
翻译:本文对概率集合与映射进行了探索、实现及修订,尤其聚焦于Bloomier过滤器及相关数据结构。论文引入融合XOR查找表(FXLT),这是一种融合空间耦合、线性构造与优化策略的增强型Bloomier过滤器版本。作者采用C语言和Python实现了该结构,并将其与布隆过滤器、XOR过滤器、二元融合过滤器、哈希表及红黑树等数据结构进行了性能对比。实验表明,FXLT在空间效率和时间效率上均优于传统Bloomier过滤器,在处理大规模数据集时与哈希表性能相当。