arXiv is a repository of electronic preprints approved for posting after moderation, but not full peer review. It consists of scientific papers in the fields of mathematics, physics, astronomy, electrical engineering, computer science, quantitative biology, statistics, mathematical finance and economics, which can be accessed online.
Many machine learning articles will be posted on arXiv before publication. In theoretical computer science and machine learning, over 60% of published papers have arXiv e-prints (Sutton et al. 2017).
Few-shot learning methods have been developed to explicitly optimize machine learning models that predict new classes using only a few labelled examples per class. Few-shot learners use prior knowledge, and can generalize to new tasks containing only a few samples with supervised information (Wang et al., 2020).
How many e-prints on Few-Shot Learning will be published on arXiv over the 2020-12-14 to 2027-01-01 period?
This question resolves as the total number of Few-Shot Learning e-prints published on arXiv over the 2020-12-14 to 2027-01-01 period (inclusive), as per the e-print's "original submission date".
Details of the search query
For the purpose of this question, Few-Shot Learning e-prints are those published under Computer Science that contain any of the following key words in "all fields":
"few shot", "1-shot", "one-shot", "five-shot", "10-shot", "ten-shot", "zero shot", "0 shot", "low-shot learning", "small sample learning"
The query should include cross-listed papers (papers listed on other subjects besides Computer Science).
The query can be executed here. Running this query for previous years gives:
- 203 for the calendar year 2017
- 350 for the calendar year 2018
- 700 for the calendar year 2019