arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.03029cs.DBcs.LG
收藏

压缩(多维)学习的Bloom过滤器

Compressing (Multidimensional) Learned Bloom Filters

TU Kaiserslautern(凯泽斯劳滕工业大学)

Angjela Davitkova, Damjan Gjurovski, Sebastian Michel

摘要:

布隆过滤器是广泛使用的数据结构,其压缩表示元素集合。查询布隆过滤器可以显示元素是否不包括在基础集合中,或者是否以特定的出错率包括在基础集合中。这种成员资格测试可以建模为二进制分类问题,并通过深度学习模型解决,从而产生所谓的学习布隆过滤器。我们已经确定,只有在考虑大量数据时,学习的布隆过滤器的好处才是显而易见的,即使这样,也有可能进一步减少其内存消耗。出于这个原因,我们引入了一种无损输入压缩技术,该技术可以提高学习模型的内存消耗,同时保持相当的模型精度。我们评估我们的方法,并显示显着的内存消耗的改进,学习布隆过滤器。

英文摘要:

Bloom filters are widely used data structures that compactly represent sets of elements. Querying a Bloom filter reveals if an element is not included in the underlying set or is included with a certain error rate. This membership testing can be modeled as a binary classification problem and solved through deep learning models, leading to what is called learned Bloom filters. We have identified that the benefits of learned Bloom filters are apparent only when considering a vast amount of data, and even then, there is a possibility to further reduce their memory consumption. For that reason, we introduce a lossless input compression technique that improves the memory consumption of the learned model while preserving a comparable model accuracy. We evaluate our approach and show significant memory consumption improvements over learned Bloom filters.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑