Transactions of the Association for Computational Linguistics (May 2023)

Erasure of Unaligned Attributes from Neural Representations

  • Shun Shao,
  • Yftah Ziser,
  • Shay B. Cohen

DOI
https://doi.org/10.1162/tacl_a_00558
Journal volume & issue
Vol. 11
pp. 488 – 510

Abstract

Read online

AbstractWe present the Assignment-Maximization Spectral Attribute removaL (AMSAL) algorithm, which erases information from neural representations when the information to be erased is implicit rather than directly being aligned to each input example. Our algorithm works by alternating between two steps. In one, it finds an assignment of the input representations to the information to be erased, and in the other, it creates projections of both the input representations and the information to be erased into a joint latent space. We test our algorithm on an extensive array of datasets, including a Twitter dataset with multiple guarded attributes, the BiasBios dataset, and the BiasBench benchmark. The latter benchmark includes four datasets with various types of protected attributes. Our results demonstrate that bias can often be removed in our setup. We also discuss the limitations of our approach when there is a strong entanglement between the main task and the information to be erased.1