Parameter-efficient Modularised Bias Mitigation via AdapterFusion
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.
Code (1)
Tasks
AttributeFairnessMulti-Task LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Analysis of AdvFusion: Adapter-based Multilingual Learning for Code Large Language Models
Programming languages can benefit from one another by utilizing a language model for software engineering tasks. Full fine-tuning and Parameter Efficient Fine-Tuning (PEFT) of Code Language Models (Code-LMs) has been exp…
Method name predictionCode TranslationCode GenerationMerA: Merging Pretrained Adapters For Few-Shot Learning
Adapter tuning, which updates only a few parameters, has become a mainstream method for fine-tuning pretrained language models to downstream tasks. However, it often yields subpar results in few-shot learning. AdapterFus…
Few-Shot LearningMRPCAdapterFusion: Non-Destructive Task Composition for Transfer Learning
Sequential fine-tuning and multi-task learning are methods aiming to incorporate knowledge from multiple tasks; however, they suffer from catastrophic forgetting and difficulties in dataset balancing. To address these sh…
Language ModellingMulti-Task LearningTransfer LearningScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale
Multi-task learning (MTL) has shown considerable practical benefits, particularly when using language models (LMs). While this is commonly achieved by learning $n$ tasks under a joint optimization procedure, some methods…
Multi-Task LearningTransfer LearningDifferent Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML
With fairness concerns gaining significant attention in Machine Learning (ML), several bias mitigation techniques have been proposed, often compared against each other to find the best method. These benchmarking efforts …
BenchmarkingFairnessfeature selectionHyperparameter Optimization