Enhancing Similarity Search Throughput by Dynamic Query Reordering
| Authors | |
|---|---|
| Year of publication | 2016 |
| Type | Article in Proceedings |
| Conference | Database and Expert Systems Applications: 27th International Conference, DEXA 2016, Porto, Portugal, September 5-8, 2016, Proceedings, Part II |
| MU Faculty or unit | |
| Citation | |
| Doi | http://dx.doi.org/10.1007/978-3-319-44406-2_14 |
| Field | Informatics |
| Keywords | Stream processing; Similarity Search |
| Description | A lot of multimedia data are being created nowadays, which can only be searched by content since no searching metadata are available for them. To make the content search efficient, similarity indexing structures based on the metric-space model can be used. In our work, we focus on a scenario where the similarity search is used in the context of stream processing. In particular, there is a potentially infinite sequence (stream) of query objects, and a query needs to be executed for each of them. The goal is to maximize the throughput of processed queries while maintaining an acceptable delay. We propose an approach based on dynamic reordering of the incoming queries combined with caching of recent results. We were able to achieve up to 3.7 times higher throughput compared to the base case when no reordering and caching is used. |
| Related projects: |