Sample Selection Bias Correction Theory
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
This paper presents a theoretical analysis of sample selection bias correction. The sample bias correction technique commonly used in machine learning consists of reweighting the cost of an error on each training point of a biased sample to more closely reflect the unbiased distribution. This relies on weights derived by various estimation techniques based on finite samples. We analyze the effect of an error in that estimation on the accuracy of the hypothesis returned by the learning algorithm for two estimation techniques: a cluster-based estimation technique and kernel mean matching. We also report the results of sample bias correction experiments with several data sets using these techniques. Our analysis is based on the novel concept of distributional stabilitywhich generalizes the existing concept of point-based stability. Much of our work and proof techniques can be used to analyze other importance weighting techniques and their effect on accuracy when using a distributionally stable algorithm.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“One of the most pertinent issues is the perennial problem of sampling/selection bias , which is an unavoidable issue in just about every statistical study. 24”
From Machine learning for large‐scale wearable sensor data in Parkinson's disease: Concepts, promises, pitfalls, and futures (2016) · cites this paper as [24]
Citations
Cites
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Self-citationCortes, C., & Vapnik, V. (1995) · Machine-mediated learning · doi:10.1023/a:1022627411411 · Cited by 48,445
Self-citationSample Selection Bias as a Specification Error
Heckman, J. J. (1979) · Econometrica · doi:10.2307/1912352 · Cited by 28,779
Wu, Y. (1999) · Technometrics · doi:10.1080/00401706.1999.10485951 · Cited by 27,221
Classification and Regression Trees.
Ryzin, J. V., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1986) · Journal of the American Statistical Association · doi:10.2307/2288003 · Cited by 20,825
Statistical Analysis With Missing Data
Lahiff, M., Little, R. J. A., & Rubin, D. B. (1989) · Journal of the American Statistical Association · doi:10.2307/2289883 · Cited by 17,265
Classification and regression trees
Praagman, J. (1985) · European Journal of Operational Research · doi:10.1016/0377-2217(85)90321-2 · Cited by 10,053
Statistical Analysis with Missing Data.
Chatfield, C., Little, R. J. A., & Rubin, D. B. (1988) · Journal of the Royal Statistical Society. Series A (Statistics in Society) · doi:10.2307/2982783 · Cited by 2,202
The foundations of cost-sensitive learning
Elkan, C. (2001) · Cited by 1,945
Correcting Sample Selection Bias by Unlabeled Data
Huang, J., Smola, A. J., Gretton, A., Borgwardt, K. M., & Schölkopf, B. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0080 · Cited by 1,571
Ridge Regression Learning Algorithm in Dual Variables
Saunders, C. J., Gammerman, A., & Vovk, V. (1998) · ePrints Soton (University of Southampton) · Cited by 811
Learning and evaluating classifiers under sample selection bias
Zadrozny, B. (2004) · Twenty-first international conference on Machine learning - ICML '04 · doi:10.1145/1015330.1015425 · Cited by 800 · cited 2×
“…bounds hold for R ( h ) and R ( h ) . b When the sampling probability is independent of the labels, as it is commonly assumed in many settings (Zadrozny 2004; 2003), Pr[ s = 1 z ] = Pr[ s = 1 x ] , and Equation 5 can be re-written as In that case, the probabilities Pr[ s = 1] and Pr[ s = 1 x…”
BackgroundDirect importance estimation with model selection and its application to covariate shift adaptation
Sugiyama, M., Nakajima, S., Kashima, H., von Bünau, P., & Kawanabe, M. (2009) · Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft) · Cited by 719
Cost-sensitive learning by cost-proportionate example weighting
Zadrozny, B., Langford, J., & Abe, N. (2004) · Third IEEE International Conference on Data Mining · doi:10.1109/icdm.2003.1250950 · Cited by 680 · cited 2×
“This weight is used to emphasize or de-emphasize the cost of an error on z i as in the so-called importance weighting or cost-sensitive learning (Elkan, 2001; Zadrozny et al., 2003).”
BackgroundMethod(2000) · CrossRef Listing of Deleted DOIs · doi:10.1162/153244302760200704 · Cited by 636
Direct importance estimation for covariate shift adaptation
Sugiyama, M., Suzuki, T., Nakajima, S., Kashima, H., von Bünau, P., & Kawanabe, M. (2008) · Annals of the Institute of Statistical Mathematics · doi:10.1007/s10463-008-0197-x · Cited by 426
Discriminative learning for differing training and test distributions
Bickel, S., Brückner, M., & Scheffer, T. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273507 · Cited by 387
Distribution-free performance bounds for potential function rules
Devroye, L., & Wagner, T. (1979) · IEEE Transactions on Information Theory · doi:10.1109/tit.1979.1056087 · Cited by 226
(2000) · CrossRef Listing of Deleted DOIs · doi:10.1162/153244302760185252 · Cited by 212
Correcting sample selection bias in maximum entropy density estimation
Dudík, M., Phillips, S. J., & Schapire, R. E. (2005) · Cited by 197
Algorithmic stability and sanity-check bounds for leave-one-out cross-validation
Kearns, M. J., & Ron, D. (1997) · Conference on Learning Theory · doi:10.1145/267460.267491 · Cited by 123
An Improved Categorization of Classifier’s Sensitivity on Sample Selection Bias
Fan, W., Davidson, I., Zadrozny, B., & Yu, P. S. (2006) · Fifth IEEE International Conference on Data Mining (ICDM'05) · doi:10.1109/icdm.2005.24 · Cited by 60
Hierarchical maximum entropy density estimation
Dudík, M., Blei, D. M., & Schapire, R. E. (2007) · International Conference on Machine Learning · doi:10.1145/1273496.1273528 · Cited by 31
Cited by
(2012) · MPG.PuRe (Max Planck Society) · doi:10.5555/2188385.2188410 · Cited by 3,603
A theory of learning from different domains
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., & Vaughan, J. W. (2010) · Machine Learning · doi:10.1007/s10994-009-5152-4 · Cited by 3,515
“A well-studied variant of this is covariate shift, which has seen significant work in recent years (Huang et al. 2007; Sugiyama et al. 2008; Cortes et al. 2008).”
BackgroundGMC: Graph-Based Multi-View Clustering
Wang, H., Yang, Y., & Liu, B. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2903810 · Cited by 952
Ad click prediction: a view from the trenches
McMahan, H. B., Holt, G., Sculley, D., Young, M., Ebner, D., Grady, J., Nie, L., Phillips, T., Davydov, E., Golovin, D., et al. (2013) · Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2487575.2488200 · Cited by 867
An Introduction to Machine Learning
Badillo, S., Banfai, B., Birzele, F., Davydov, I. I., Hutchinson, L., Kam‐Thong, T., Siebourg‐Polster, J., Steiert, B., & Zhang, J. D. (2020) · Clinical Pharmacology & Therapeutics · doi:10.1002/cpt.1796 · Cited by 799
Metadata
- Authors
- Cortes, C., Mohri, M., Riley, M., & Rostamizadeh, A.
- Affiliations
- Google (United States) (US)
- Courant Institute of Mathematical Sciences (US)
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2008
- Pages
- 38-53
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W1853837125
- Cited by
- 272
- References
- 23
- Citations by year
- 2026: 8 · 2025: 9 · 2024: 11 · 2023: 24 · 2022: 22 · 2021: 22 · 2020: 33 · 2019: 25 · 2018: 21 · 2017: 16 · 2016: 17 · 2015: 11 · 2014: 16 · 2013: 8 · 2012: 9
- FWCI
- 4.95
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Lecture notes in computer science (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Physical Sciences › Computer Science › Artificial Intelligence › Imbalanced Data Classification Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- sample selection bias, bias correction, importance weighting, kernel mean matching, training data bias
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.