Open AccessPosted Content
Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
Reads0
Chats0
TLDR
An adversarial training procedure is used to remove information about the sensitive attribute from the latent representation learned by a neural network, and the data distribution empirically drives the adversary's notion of fairness.Abstract:
How can we learn a classifier that is "fair" for a protected or sensitive group, when we do not know if the input to the classifier belongs to the protected group? How can we train such a classifier when data on the protected group is difficult to attain? In many settings, finding out the sensitive input attribute can be prohibitively expensive even during model training, and sometimes impossible during model serving. For example, in recommender systems, if we want to predict if a user will click on a given recommendation, we often do not know many attributes of the user, e.g., race or age, and many attributes of the content are hard to determine, e.g., the language or topic. Thus, it is not feasible to use a different classifier calibrated based on knowledge of the sensitive attribute.
Here, we use an adversarial training procedure to remove information about the sensitive attribute from the latent representation learned by a neural network. In particular, we study how the choice of data for the adversarial training effects the resulting fairness properties. We find two interesting results: a small amount of data is needed to train these adversarial models, and the data distribution empirically drives the adversary's notion of fairness.read more
Citations
More filters
Posted Content
Null-sampling for Interpretable and Fair Representations
TL;DR: This work introduces an adversarially trained model with a null-sampling procedure to produce invariant representations in the data domain, and shows the effectiveness of the method on both image and tabular datasets: Coloured MNIST, the CelebA and the Adult dataset.
Posted Content
Practical Compositional Fairness: Understanding Fairness in Multi-Task ML Systems.
TL;DR: This paper provides theory that demonstrates a set of conditions under which fairness of individual models does compose, and presents an analytical framework for both understanding whether a system's signals can achieve compositional fairness, and diagnosing which of these signals lowers the overall system's end-to-end fairness the most.
Proceedings ArticleDOI
Improving Recommendation Fairness via Data Augmentation
TL;DR: In this paper , the authors proposed a data augmentation framework to improve recommendation fairness from a data augmentation perspective, where each user in one group has a similar item preference (click or non-click) as the item preference of any user in the remaining group.
Posted Content
Fairness-Aware Online Personalization.
TL;DR: A model is constructed for generating training data with potentially biased features as well as potentially biased labels and the extent of bias that is learned by the model when the user responds in a biased manner as in many real-world scenarios is quantified.
Posted Content
A Review of Generative Adversarial Networks in Cancer Imaging: New Applications, New Solutions.
Richard Osuala,Kaisar Kushibar,Lidia Garrucho,Akis Linardos,Zuzanna Szafranowska,Stefan Klein,Ben Glocker,Oliver Diaz,Karim Lekadir +8 more
TL;DR: In this article, the authors assess the potential of GANs to address a number of key challenges of cancer imaging, including data scarcity and imbalance, domain and dataset shifts, data access and privacy, data annotation and quantification, as well as cancer detection, tumour profiling and treatment planning.
References
More filters
Proceedings Article
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization.
TL;DR: Adaptive subgradient methods as discussed by the authors dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradient-based learning, which allows us to find needles in haystacks in the form of very predictive but rarely seen features.
Journal Article
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
TL;DR: This work describes and analyze an apparatus for adaptively modifying the proximal function, which significantly simplifies setting a learning rate and results in regret guarantees that are provably as good as the best proximal functions that can be chosen in hindsight.
Book ChapterDOI
Domain-adversarial training of neural networks
Yaroslav Ganin,Evgeniya Ustinova,Hana Ajakan,Pascal Germain,Hugo Larochelle,François Laviolette,Mario Marchand,Victor Lempitsky +7 more
TL;DR: In this article, a new representation learning approach for domain adaptation is proposed, in which data at training and test time come from similar but different distributions, and features that cannot discriminate between the training (source) and test (target) domains are used to promote the emergence of features that are discriminative for the main learning task on the source domain.
Proceedings Article
Equality of opportunity in supervised learning
TL;DR: This work proposes a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features and shows how to optimally adjust any learned predictor so as to remove discrimination according to this definition.