Fetching the paper…
Reading the bibliography…
Model-induced distribution shifts (MIDS) occur as previous model outputs pollute new model training sets over generations of models.
Invariant risk minimization, 2020
M. Arjovsky, L. Bottou, I. Gulrajani, and D. Lopez-Paz · 1907
Earlier work this paper cites.
Fair generative modeling via weak supervision
A. Grover, K. Choi, T. Singh, R. Shu, and S. Ermon · 1910
Earlier work this paper cites.
On the applicability of machine learning fairness notions
K. Makhlouf, S. Zhioua, and C. Palamidessi · 1931
Earlier work this paper cites.
Underwriting Manual: Underwriting and Valuation Procedure Under Title 2 of the National Housing Act
F. H. Administration · 1938
Earlier work this paper cites.
82 Stat. 73 - An Act to prescribe penalties for certain acts of violence or intimidation, and for other purposes, 1968
90th United States Congress · 1968
Earlier work this paper cites.
Iterative reclassification procedure for constructing an asymptotically optimal rule of allocation in discriminant analysis
G. J. McLachlan · 1975
Earlier work this paper cites.
The combahee river collective statement, April 1977
T. C. R. Collective · 1977
Earlier work this paper cites.
Crabgrass frontier: the suburbanization of the United States
K. T. Jackson · 1985
Earlier work this paper cites.
Introduction: The embeddedness of economic markets in economics
M. Callon · 1998
Earlier work this paper cites.
Curriculum labeling: Self-paced pseudo-labeling for semi-supervised learning
P. Cascante-Bonilla, F. Tan, Y. Qi, and V. Ordonez · 2001
Earlier work this paper cites.
J. C. Perdomo, T. Zrnic, C. Mendler-Dünner, and M. Hardt · 2002
Earlier work this paper cites.
Building classifiers with independency constraints
T. Calders, F. Kamiran, and M. Pechenizkiy · 2009
Earlier work this paper cites.
Reading digits in natural images with unsupervised feature learning
Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, and A. Y. Ng · 2011
Earlier work this paper cites.
Mt detection in web-scraped parallel corpora
S. Rarrick, C. Quirk, and W. D. Lewis · 2011
Earlier work this paper cites.
The MNIST database of handwritten digit images for machine learning research
L. Deng · 2012
Earlier work this paper cites.
Learning fair representations
R. Zemel, Y. Wu, K. Swersky, T. Pitassi, and C. Dwork · 2013
Earlier work this paper cites.
Distilling the knowledge in a neural network, 2015
G. Hinton, O. Vinyals, and J. Dean · 2015
Earlier work this paper cites.
Deep learning face attributes in the wild
Z. Liu, P. Luo, X. Wang, and X. Tang · 2015
Earlier work this paper cites.
Fair prediction with disparate impact: A study of bias in recidivism prediction instruments, 2016
A. Chouldechova · 2016
Earlier work this paper cites.
COMPAS risk scales : Demonstrating accuracy equity and predictive parity performance of the COMPAS risk scales in Broward county, 2016
N. I. R. Department · 2016
Earlier work this paper cites.
Equality of opportunity in supervised learning
M. Hardt, E. Price, and N. Srebro · 2016
Earlier work this paper cites.
To Predict and Serve?
K. Lum and W. Isaac · 2016
Earlier work this paper cites.
Algorithmic decision making and the cost of fairness
S. Corbett-Davies, E. Pierson, A. Feller, S. Goel, and A. Huq · 2017
Earlier work this paper cites.
Runaway feedback loops in predictive policing
D. Ensign, S. A. Friedler, S. Neville, C. E. Scheidegger, and S. Venkatasubramanian · 2017
Earlier work this paper cites.
Introducing intersectionality
M. Romero · 2017
Cited alongside, same era.
Gender shades: Intersectional accuracy disparities in commercial gender classification
J. Buolamwini and T. Gebru · 2018
Cited alongside, same era.
Fairness without demographics in repeated loss minimization
T. B. Hashimoto, M. Srivastava, H. Namkoong, and P. Liang · 2018
Cited alongside, same era.
Inherent trade-offs in algorithmic fairness
J. Kleinberg · 2018
Cited alongside, same era.
2018 differential privacy synthetic data challenge, 2018
NIST · 2018
Cited alongside, same era.
Fairwashing: the risk of rationalization
U. Aivodji, H. Arai, O. Fortineau, S. Gambs, S. Hara, and A. Tapp · 2019
Cited alongside, same era.
Robin hood and matthew effects: Differential privacy has disparate impact on synthetic data
G. Ganev, B. Oprisanu, and E. D. Cristofaro · 2022
Later among the works it cites.
Will large-scale generative models corrupt future datasets?
R. Hataya, H. Bao, and H. Arai · 2022
Later among the works it cites.
FairGAN: GANs-based fairness-aware learning for recommendations with implicit feedback
J. Li, Y. Ren, and K. Deng · 2022
Later among the works it cites.
A quantitative analysis of labeling issues in the CelebA dataset
B. Lingenfelter, S. R. Davis, and E. M. Hand · 2022
Later among the works it cites.
Rules for Archival Description (RAD)
RAD · 2022
Later among the works it cites.
Linking environmental injustices in Detroit, MI to institutional racial segregation through historical federal redlining
A. Shkembi, L. M. Smith, and R. L. Neitzel · 2022
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Bias correction of learned generative models using likelihood-free importance weighting, 2019b
A. Grover, J. Song, A. Agarwal, K. Tran, A. Kapoor, E. Horvitz, and S. Ermon · 2019
Cited alongside, same era.
Dirty data, bad predictions: How civil rights violations impact police data, predictive policing systems, and justice, February 2019
R. Richardson, J. Schultz, and K. Crawford · 2019
Cited alongside, same era.
VAE-pytorch
S. K. Sujit · 2019
Cited alongside, same era.
Fairlearn: A toolkit for assessing and improving fairness in AI
S. Bird, M. Dudík, R. Edgar, B. Horn, R. Lutz, V. Milan, M. Sameki, H. Wallach, and K. Walker · 2020
Cited alongside, same era.
Data feminism
C. D’Ignazio and L. F. Klein · 2020
Cited alongside, same era.
The false promise of risk assessments: Epistemic reform and the limits of fairness
B. Green · 2020
Cited alongside, same era.
Later among the works it cites.
Beyond fairness: Reparative algorithms to address historical injustices of housing discrimination in the US
W. So, P. Lothia, R. Pimplikar, A. Hosoi, and C. D’Ignazio · 2022
Later among the works it cites.
Synthetic data – anonymisation groundhog day
T. Stadler, B. Oprisanu, and C. Troncoso · 2022
Later among the works it cites.
Machine learning approaches to predict loan default
W. Wu · 2022
Later among the works it cites.
The rich get richer: Disparate impact of semi-supervised learning
Z. Zhu, T. Luo, and Y. Liu · 2022
Later among the works it cites.
Self-consuming generative models go MAD, 2023
S. Alemohammad, J. Casco-Rodriguez, L. Luzi, A. I. Humayun, H. Babaei, D. LeJeune, A. Siahkoohi, and R. G. Baraniuk · 2023
Later among the works it cites.
Simplicity bias leads to amplified performance disparities
S. J. Bell and L. Sagun · 2023
Later among the works it cites.
Describing Archives: A Content Standard (DACS), an Implementation of General International Standard Archival Description (ISAD(G))
DACS · 2023
Later among the works it cites.
Performative prediction: Past and future, 2023
M. Hardt and C. Mendler-Dünner · 2023
Later among the works it cites.
Proper ResNet implementation for CIFAR10/CIFAR100 in PyTorch
Y. Idelbayev · 2023
Later among the works it cites.
A hunt for the snark: Annotator diversity in data practices
S. Kapania, A. S. Taylor, and D. Wang · 2023
Later among the works it cites.
Towards understanding the interplay of generative artificial intelligence and the internet, 2023
G. Martínez, L. Watson, P. Reviriego, J. A. Hernández, M. Juarez, and R. Sarkar · 2023
Later among the works it cites.
Impact of classification difficulty on the weight matrices spectra in deep learning and application to early-stopping
X. Meng and J. Yao · 2023
Later among the works it cites.
Envisioning information access systems: What makes for good tools and a healthy web?
C. Shah and E. M. Bender · 2023
Later among the works it cites.
The curse of recursion: Training on generated data makes models forget, 2023
I. Shumailov, Z. Shumaylov, Y. Zhao, Y. Gal, N. Papernot, and R. Anderson · 2023
Later among the works it cites.
Data feedback loops: Model-driven amplification of dataset biases
R. Taori and T. Hashimoto · 2023
Later among the works it cites.
Navigating the feedback loop in recommender systems: Insights and strategies from industry practice
D. Tong, Q. Qiao, T.-P. Lee, J. McInerney, and J. Basilico · 2023
Later among the works it cites.
Artificial artificial artificial intelligence: Crowd workers widely use large language models for text production tasks, 2023
V. Veselovsky, M. H. Ribeiro, and R. West · 2023
Later among the works it cites.
The non-white popultion of metropolitan Detroit, 1955
Detroit Deomgraphics · 2027
Closest in time.