Stable and Semi-stable Sampling Approaches for Continuously Used Samples

March 02, 2022 Β· Declared Dead Β· πŸ› Knowledge and Information Systems

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Nikita Astrakhantsev, Deepak Chittajallu, Nabeel Kaushal, Vladislav Mokeev arXiv ID 2203.01381 Category cs.IR: Information Retrieval Cross-listed cs.LG Citations 0 Venue Knowledge and Information Systems Last Checked 4 months ago
Abstract
Information retrieval systems are usually measured by labeling the relevance of results corresponding to a sample of user queries. In practical search engines, such measurement needs to be performed continuously, such as daily or weekly. This creates a trade-off between (a) representativeness of query sample to current query traffic of the product; (b) labeling cost: if we keep the same query sample, results would be similar allowing us to reuse their labels; and (c) overfitting caused by continuous usage of same query sample. In this paper we explicitly formulate this tradeoff, propose two new variants -- Stable and Semi-stable -- to simple and weighted random sampling and show that they outperform existing approaches for the continuous usage settings, including monitoring/debugging search engine or comparing ranker candidates.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Information Retrieval

Died the same way β€” πŸ‘» Ghosted