Advertisement

Latency Control

  • Guoliang Li
  • Jiannan Wang
  • Yudian Zheng
  • Ju Fan
  • Michael J. Franklin
Chapter

Abstract

Latency refers to the total time of completing a job. Since humans are slower than machines, sometimes even a simple job (e.g., labeling one thousand images) may take hours or even days to complete. Thus, another big challenge in crowdsourced data management is latency control, that is, how to reduce job completion time while still keeping good result quality as well as low cost.

References

  1. 1.
    Bernstein, M.S., Brandt, J., Miller, R.C., Karger, D.R.: Crowds in two seconds: enabling realtime crowd-powered interfaces. In: UIST, pp. 33–42 (2011)Google Scholar
  2. 2.
    Faradani, S., Hartmann, B., Ipeirotis, P.G.: What’s the right price? pricing tasks for finishing on time. In: AAAI Workshop (2011)Google Scholar
  3. 3.
    Gao, Y., Parameswaran, A.G.: Finish them! Pricing algorithms for human computation. PVLDB 7(14), 1965–1976 (2014)Google Scholar
  4. 4.
    Haas, D., Wang, J., Wu, E., Franklin, M.J.: Clamshell: Speeding up crowds for low-latency data labeling. PVLDB 9(4), 372–383 (2015)Google Scholar
  5. 5.
    Sarma, A.D., Parameswaran, A.G., Garcia-Molina, H., Halevy, A.Y.: Crowd-powered find algorithms. In: ICDE, pp. 964–975 (2014)Google Scholar
  6. 6.
    Verroios, V., Lofgren, P., Garcia-Molina, H.: tdp: An optimal-latency budget allocation strategy for crowdsourced MAXIMUM operations. In: SIGMOD, pp. 1047–1062 (2015)Google Scholar
  7. 7.
    Yan, T., Kumar, V., Ganesan, D.: Crowdsearch: exploiting crowds for accurate real-time image search on mobile phones. In: MobiSys, pp. 77–90 (2010)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Guoliang Li
    • 1
  • Jiannan Wang
    • 2
  • Yudian Zheng
    • 3
  • Ju Fan
    • 4
  • Michael J. Franklin
    • 5
  1. 1.Department of Computer Science and TechnologyTsinghua UniversityBeijingChina
  2. 2.School of Computing ScienceSimon Fraser UniversityBurnabyCanada
  3. 3.Twitter Inc.San FranciscoUSA
  4. 4.DEKE Lab & School of InformationRenmin University of ChinaBeijingChina
  5. 5.Department of Computer ScienceUniversity of ChicagoChicagoUSA

Personalised recommendations