You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time
Abstract: Deep neural networks are prone to various bias issues, jeopardizing their applications for high-stake decision-making. Existing fairness methods typically offer a fixed accuracy-fairness trade-off at the inference time, since the weight of the well-trained model is a fixed point (fairness-optimum) in the weight space. Nevertheless, more flexible accuracy-fairness trade-offs at the inference time are practically desired since: 1) stakes of the same downstream task can vary for different individuals, and 2) different regions have diverse laws or regularization for fairness. If using the previous fairness methods, we have to train multiple models, each offering a specific level of accuracy-fairness trade-off. This is often computationally expensive, time-consuming, and difficult to deploy, making it less practical for real-world applications. To address this problem, we propose \textit{You Only Debias Once} (YODO) to achieve in-situ flexible accuracy-fairness trade-offs at the inference time, using \textit{a single model} that trained only once. Instead of pursuing one individual fixed point (fairness-optimum) in the weight space, we aim to find a ``line'' in the weight space that connects the accuracy-optimum and fairness-optimum points using a single model. Points (models) on this line implement varying levels of accuracy-fairness trade-offs. At the inference time, by manually selecting the specific position of the learned ``line'', our proposed method can achieve arbitrary accuracy-fairness trade-offs for different end-users and scenarios. Experimental results on tabular and image datasets show that YODO achieves flexible trade-offs between model accuracy and fairness, at ultra-low overheads. Our codes are anonymously available at https://anonymous.4open.science/r/yodo-BB81 .
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~bo_han2
Submission Number: 914
Loading