Meta-Sketch: A Neural Data Structure for Estimating Item Frequencies of Data Streams
Abstract
To estimate item frequencies of data streams with limited space, sketches are widely used in real applications, including real-time web analytics, network monitoring, and self-driving. Sketches can be viewed as a model which maps the identifier of a stream item to the corresponding frequency domain. Starting from the premise, we envision a neural data structure, which we term the meta-sketch, to go beyond the basic structure of conventional sketches. The meta-sketch learns basic sketching abilities from meta-tasks constituted with synthetic datasets following Zipf distributions in the pre-training phase, and can be fast adapted to real (skewed) distributions in the adaption phase. Extensive experiments demonstrate the performance gains of the meta-sketch and offer insights into our proposals.
Cite
Text
Cao et al. "Meta-Sketch: A Neural Data Structure for Estimating Item Frequencies of Data Streams." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I6.25846Markdown
[Cao et al. "Meta-Sketch: A Neural Data Structure for Estimating Item Frequencies of Data Streams." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/cao2023aaai-meta/) doi:10.1609/AAAI.V37I6.25846BibTeX
@inproceedings{cao2023aaai-meta,
title = {{Meta-Sketch: A Neural Data Structure for Estimating Item Frequencies of Data Streams}},
author = {Cao, Yukun and Feng, Yuan and Xie, Xike},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2023},
pages = {6916-6924},
doi = {10.1609/AAAI.V37I6.25846},
url = {https://mlanthology.org/aaai/2023/cao2023aaai-meta/}
}