Adversarial Removal of Demographic Attributes from Text Data

08/20/2018
by   Yanai Elazar, et al.
0

Recent advances in Representation Learning and Adversarial Training seem to succeed in removing unwanted features from the learned representation. We show that demographic information of authors is encoded in -- and can be recovered from -- the intermediate representations learned by text-based neural classifiers. The implication is that decisions of classifiers trained on textual data are not agnostic to -- and likely condition on -- demographic attributes. When attempting to remove such demographic information using adversarial training, we find that while the adversarial component achieves chance-level development-set accuracy during training, a post-hoc classifier, trained on the encoded sentences from the first part, still manages to reach substantially higher classification accuracies on the same data. This behavior is consistent across several tasks, demographic properties and datasets. We explore several techniques to improve the effectiveness of the adversarial component. Our main conclusion is a cautionary one: do not rely on the adversarial training to achieve invariant representation to sensitive features.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/08/2022

Probing Classifiers are Unreliable for Concept Removal and Detection

Neural network models trained on text data have been found to encode und...
research
04/28/2023

On the existence of solutions to adversarial training in multiclass classification

We study three models of the problem of adversarial training in multicla...
research
06/09/2022

Unlearning Protected User Attributes in Recommendations with Adversarial Training

Collaborative filtering algorithms capture underlying consumption patter...
research
03/09/2023

Identification of Systematic Errors of Image Classifiers on Rare Subgroups

Despite excellent average-case performance of many image classifiers, th...
research
12/17/2018

BriarPatches: Pixel-Space Interventions for Inducing Demographic Parity

We introduce the BriarPatch, a pixel-space intervention that obscures se...
research
04/29/2023

Adversarial Representation Learning for Robust Privacy Preservation in Audio

Sound event detection systems are widely used in various applications su...
research
06/07/2023

Migrate Demographic Group For Fair GNNs

Graph Neural networks (GNNs) have been applied in many scenarios due to ...

Please sign up or login with your details

Forgot password? Click here to reset