Limitations and future directions of “Data Shapley: Equitable Valuation of Data for Machine Learning”
Keywords:
Date Shapley, Data value, Data privacy, Machine learning, NP problemsAbstract
This paper addresses the questions “What are the limitations of the results?” and “List a few possible future directions.” Specifically, I answers the limitations of the method pro- posed in the paper “What is your data worth? Equitable Valuation of Data,” focusing on whether Shapley values can truly measure the value of data, Monte Carlo methods, and data privacy aspects. Then, I proposes three mathematical models for estimating data value as future research direc- tions, including new model identification, heuristic search, and NP approximation problems. Additionally, I suggests future research directions based on the practicality of the data Shapley method, data block partitioning, and privacy protection.
References
Posner, E. A. Weyl, E. G. Radical Markets: Uprooting Capitalism and Democracy for a Just Society (Princeton Uni- versity Press, 2018).
Shapley, L. S. A value for n-person games. Contribu- tions to Theory Games 2, 307–317 (1953).
Mann, I. Shapley, L. S. Values of large games. 6: Evalu- ating the electoral college exactly. Tech. Rep., RAND CORP SANTA MONICA CA (1962).
Hull,J. J. A database for handwritten text recognition research. IEEE Transactions on pattern analysis machine intelligence 16, 550–554 (1994).
Cook, R. D. Weisberg, S. Residuals and influence in regression (New York: Chapman and Hall, 1982).
Wolf,L., Hassner, T. Taigman,Y. Effective unconstrained face recognition by combining multiple descriptors and learned background statistics. IEEE transactions on pattern analysis machine intelligence 33, 1978–1990 (2011).
Buolamwini,J. Gebru,T. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on Fairness, Accountability and Transparency, 77–91 (2018).
Steinhardt,J., Koh, P. W. W. Liang, P. S. Certified de- fenses for data poisoning attacks. In Advances in Neural Information Processing Systems, 3517–3529 (2017).
Milnor, J. W. Shapley, L. S. Values of large games ii: Oceanic games. Math. operations research 3, 290–307 (1978).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Well Testing Journal
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
This license requires that re-users give credit to the creator. It allows re-users to distribute, remix, adapt, and build upon the material in any medium or format, for noncommercial purposes only.
