Adversarial Removal of Demographic Attributes Revisited

Abstract

Elazar and Goldberg (2018) showed that protected attributes can be extracted from the representations of a debiased neural network for mention detection at above-chance levels, by evaluating a diagnostic classifier on a heldout subsample of the data it was trained on. We revisit their experiments and conduct a series of follow-up experiments showing that, in fact, the diagnostic classifier generalizes poorly to both new in-domain samples and new domains, indicating that it relies on correlations specific to their particular data sample. We further show that a diagnostic classifier trained on the biased baseline neural network also does not generalize to new samples. In other words, the biases detected in Elazar and Goldberg (2018) seem restricted to their particular data sample, and would therefore not bias the decisions of the model on new samples, whether in-domain or out-of-domain. In light of this, we discuss better methodologies for detecting bias in our models.

A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations

“…1. We observe that we achieve similar scores than the ones reported in previous studies (Barrett et al, 2019;Elazar and Goldberg, 2018). This experiment shows that, when training to solve the main task, the classifier learns information about the protected attribute, i.e., the attacker's accuracy is better than random guessing.…”

“…6 shows that the cross-entropy loss leads to a lower bound (up to a constant) on the MI. Although the cross-entropy can lead to good estimates of the conditional entropy, the adversarial approaches for classification and sequence generation by (Barrett et al, 2019;John et al, 2018) which consists in maximizing the cross-entropy, induces a degeneracy (unbounded loss) as λ increases in the underlying optimization problem. As we will observe in next section, our variational upper bound in Th.…”

Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection

“…While adverserial methods showed impressive performance in various machine learning tasks, and were applied for the goal of removal of sensitive information (Elazar and Goldberg, 2018;Coavoux et al, 2018;Resheff et al, 2019;Barrett et al, 2019), they are notoriously hard to train. Elazar and Goldberg (2018) have evaluated adverserial methods for the removal of demographic information from representations.…”

Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text

“…in cross-lingual (Schuster et al, 2019;Liu et al, 2019) or multilingual settings (Cao et al, 2020). In contrast to prior work, we experiment with aligning BERT using adversarial training, which is related to using adversarial training for domain adaptation (Ganin et al, 2016), coping with bias or confounding variables (Li et al, 2018;Raff and Sylvester, 2018;Zhang et al, 2018;Barrett et al, 2019;McHardy et al, 2019) or transferring models from a source to a target language (Zhang et al, 2017;Keung et al, 2019;Wang et al, 2019). Similar to Chen and Cardie (2018), we use a multinomial discriminator in our setting.…”