FAIR: Fair adversarial instance re-weighting
Open accessThe claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
There has been work proposing the use of an adversary as a pre-processing transformation process on the training data with similar objectives to transformation yet often moving towards a notion of censoring the training data with similar objectives to variable blinding.
“There has also been work proposing the use of an adversary as a pre-processing transformation process on the training data (e.g.[1,99,162,206,234,299,300]) with similar objectives to transformation as discussed in subsection 4.4 yet often moving towards a notion of łcensoringž the training data with similar objectives to variable blinding as discussed in subsection 4.1.”
From Fairness in machine learning: A survey (2024) · cites this paper as [234]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 63 · Cited by 40
Research works printed but not linked: 5
- M. K. Domadiya, M. V. Gamit, M. K. Patel, A review on face detection and expression recognition (2019).
- M. B. Zafar, I. Valera, M. Gomez-Rodriguez, K. P. Gummadi, Fairness con- straints: A flexible approach for fair classification., Journal of Machine Learning Research 20 (75) (2019) 1-42.
- I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative adversarial nets, in: Advances in neural information processing systems, 2014, pp. 2672-2680.
- Y.-P. Hsieh, C. Liu, V. Cevher, Finding mixed nash equilibria of generative adversarial networks, in: International Conference on Machine Learning, 2019, pp. 2810-2819.
- L. Jiang, Z. Zhou, T. Leung, L.-J. Li, L. Fei-Fei, Mentornet: Learning data- driven curriculum for very deep neural networks on corrupted labels, in: Inter- national Conference on Machine Learning, 2018, pp. 2304-2313.
- Authors
- Petrović, A., Nikolić, M., Radovanović, S., Delibašić, B., & Jovanović, M.
- Affiliations
- Singidunum University (RS)
- University of Belgrade (RS)
- Corresponding author
- Petrović, Andrija
- Venue
- Neurocomputing
- Publisher
- Elsevier BV
- Published
- 2022-03
- Volume
- 476
- Pages
- 14-37
- ISSN
- 0925-2312 (ISSN-L)
- OpenAlex
- W3102319887
- Cited by
- 40
- References
- 63
- Citations by year
- 2026: 7 · 2025: 13 · 2024: 9 · 2023: 6 · 2022: 2 · 2021: 3
- FWCI
- 8.69
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- Neurocomputing (publishedVersion)
- Repository of the University of Belgrade Faculty of Organizational Sciences (RFOS) (submittedVersion, other-oa)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja (OI174021, TR35004, TR41008)
- Office of Naval Research (N62909-19–1-2008)
- Topics
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- algorithmic fairness, adversarial training, instance weighting, sensitive attributes, 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
