Techniques for Querying Big Data

The project aims to develop effective methods for querying big relations with constrained resources.

We have developed BEAS, for Bounded EvAluation of SQL queries, based on a new query evaluation paradigm known as bounded evaluation. To answer a query Q on a dataset D, the idea is to look at only a ``bounded'' fraction of D that suffices to compute query answer Q(D), instead of at the entire D. BEAS has been evaluated with CDR queries by our industry collaborators, and is found to be able to improve the performance of the data analytics by orders of magnitude.

Related link

Huawei deal to advance expertise in data science