Bias Mitigation in Fine-tuning Pre-trained Models for Enhanced Fairness
and Efficiency
- URL: http://arxiv.org/abs/2403.00625v1
- Date: Fri, 1 Mar 2024 16:01:28 GMT
- Title: Bias Mitigation in Fine-tuning Pre-trained Models for Enhanced Fairness
and Efficiency
- Authors: Yixuan Zhang and Feng Zhou
- Abstract summary: We introduce an efficient and robust fine-tuning framework specifically designed to mitigate biases in new tasks.
Our empirical analysis shows that the parameters in the pre-trained model that affect predictions for different demographic groups are different.
We employ a transfer learning strategy that neutralizes the importance of these influential weights, determined using Fisher information across demographic groups.
- Score: 26.86557244460215
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Fine-tuning pre-trained models is a widely employed technique in numerous
real-world applications. However, fine-tuning these models on new tasks can
lead to unfair outcomes. This is due to the absence of generalization
guarantees for fairness properties, regardless of whether the original
pre-trained model was developed with fairness considerations. To tackle this
issue, we introduce an efficient and robust fine-tuning framework specifically
designed to mitigate biases in new tasks. Our empirical analysis shows that the
parameters in the pre-trained model that affect predictions for different
demographic groups are different, so based on this observation, we employ a
transfer learning strategy that neutralizes the importance of these influential
weights, determined using Fisher information across demographic groups.
Additionally, we integrate this weight importance neutralization strategy with
a matrix factorization technique, which provides a low-rank approximation of
the weight matrix using fewer parameters, reducing the computational demands.
Experiments on multiple pre-trained models and new tasks demonstrate the
effectiveness of our method.
Related papers
- Low-rank finetuning for LLMs: A fairness perspective [54.13240282850982]
Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models.
This paper investigates the effectiveness of these methods in capturing the shift of fine-tuning datasets from the initial pre-trained data distribution.
We show that low-rank fine-tuning inadvertently preserves undesirable biases and toxic behaviors.
arXiv Detail & Related papers (2024-05-28T20:43:53Z) - Aggregation Weighting of Federated Learning via Generalization Bound
Estimation [65.8630966842025]
Federated Learning (FL) typically aggregates client model parameters using a weighting approach determined by sample proportions.
We replace the aforementioned weighting method with a new strategy that considers the generalization bounds of each local model.
arXiv Detail & Related papers (2023-11-10T08:50:28Z) - Debias the Training of Diffusion Models [53.49637348771626]
We provide theoretical evidence that the prevailing practice of using a constant loss weight strategy in diffusion models leads to biased estimation during the training phase.
We propose an elegant and effective weighting strategy grounded in the theoretically unbiased principle.
These analyses are expected to advance our understanding and demystify the inner workings of diffusion models.
arXiv Detail & Related papers (2023-10-12T16:04:41Z) - Gradient Surgery for One-shot Unlearning on Generative Model [0.989293617504294]
We introduce a simple yet effective approach to remove a data influence on the deep generative model.
Inspired by works in multi-task learning, we propose to manipulate gradients to regularize the interplay of influence among samples.
arXiv Detail & Related papers (2023-07-10T13:29:23Z) - FairIF: Boosting Fairness in Deep Learning via Influence Functions with
Validation Set Sensitive Attributes [51.02407217197623]
We propose a two-stage training algorithm named FAIRIF.
It minimizes the loss over the reweighted data set where the sample weights are computed.
We show that FAIRIF yields models with better fairness-utility trade-offs against various types of bias.
arXiv Detail & Related papers (2022-01-15T05:14:48Z) - Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models.
Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely.
Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
arXiv Detail & Related papers (2021-10-01T10:03:57Z) - Experimental Design for Overparameterized Learning with Application to
Single Shot Deep Active Learning [5.141687309207561]
Modern machine learning models are trained on large amounts of labeled data.
Access to large volumes of labeled data is often limited or expensive.
We propose a new design strategy for curating the training set.
arXiv Detail & Related papers (2020-09-27T11:27:49Z) - Learning Diverse Representations for Fast Adaptation to Distribution
Shift [78.83747601814669]
We present a method for learning multiple models, incorporating an objective that pressures each to learn a distinct way to solve the task.
We demonstrate our framework's ability to facilitate rapid adaptation to distribution shift.
arXiv Detail & Related papers (2020-06-12T12:23:50Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.