Parameter-efficient Modularised Bias Mitigation via AdapterFusion

Deepak Kumar, Oleg Lesota, George Zerveas, Daniel Cohen, Carsten Eickhoff, Markus Schedl, Navid Rekabsaz


Abstract
Large pre-trained language models contain societal biases and carry along these biases to downstream tasks. Current in-processing bias mitigation approaches (like adversarial training) impose debiasing by updating a model’s parameters, effectively transferring the model to a new, irreversible debiased state. In this work, we propose a novel approach to develop stand-alone debiasing functionalities separate from the model, which can be integrated into the model on-demand, while keeping the core model untouched. Drawing from the concept of AdapterFusion in multi-task learning, we introduce DAM (Debiasing with Adapter Modules) – a debiasing approach to first encapsulate arbitrary bias mitigation functionalities into separate adapters, and then add them to the model on-demand in order to deliver fairness qualities. We conduct a large set of experiments on three classification tasks with gender, race, and age as protected attributes. Our results show that DAM improves or maintains the effectiveness of bias mitigation, avoids catastrophic forgetting in a multi-attribute scenario, and maintains on-par task performance, while granting parameter-efficiency and easy switching between the original and debiased models.
Anthology ID:
2023.eacl-main.201
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2738–2751
Language:
URL:
https://aclanthology.org/2023.eacl-main.201
DOI:
10.18653/v1/2023.eacl-main.201
Bibkey:
Cite (ACL):
Deepak Kumar, Oleg Lesota, George Zerveas, Daniel Cohen, Carsten Eickhoff, Markus Schedl, and Navid Rekabsaz. 2023. Parameter-efficient Modularised Bias Mitigation via AdapterFusion. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2738–2751, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Parameter-efficient Modularised Bias Mitigation via AdapterFusion (Kumar et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.201.pdf
Video:
 https://aclanthology.org/2023.eacl-main.201.mp4