Marginal Debiased Network for Fair Visual Recognition
- URL: http://arxiv.org/abs/2401.02150v1
- Date: Thu, 4 Jan 2024 08:57:09 GMT
- Title: Marginal Debiased Network for Fair Visual Recognition
- Authors: Mei Wang, Weihong Deng, Sen Su
- Abstract summary: We propose a novel marginal debiased network (MDN) to learn debiased representations.
More specifically, a marginal softmax loss (MSL) is designed by introducing the idea of margin penalty into the fairness problem.
Our MDN can achieve a remarkable performance on under-represented samples and obtain superior debiased results against the previous approaches.
- Score: 65.64172835624206
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Deep neural networks (DNNs) are often prone to learn the spurious
correlations between target classes and bias attributes, like gender and race,
inherent in a major portion of training data (bias-aligned samples), thus
showing unfair behavior and arising controversy in the modern pluralistic and
egalitarian society. In this paper, we propose a novel marginal debiased
network (MDN) to learn debiased representations. More specifically, a marginal
softmax loss (MSL) is designed by introducing the idea of margin penalty into
the fairness problem, which assigns a larger margin for bias-conflicting
samples (data without spurious correlations) than for bias-aligned ones, so as
to deemphasize the spurious correlations and improve generalization on unbiased
test criteria. To determine the margins, our MDN is optimized through a meta
learning framework. We propose a meta equalized loss (MEL) to perceive the
model fairness, and adaptively update the margin parameters by metaoptimization
which requires the trained model guided by the optimal margins should minimize
MEL computed on an unbiased meta-validation set. Extensive experiments on
BiasedMNIST, Corrupted CIFAR-10, CelebA and UTK-Face datasets demonstrate that
our MDN can achieve a remarkable performance on under-represented samples and
obtain superior debiased results against the previous approaches.
Related papers
- Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness [10.081447621656523]
The impact on language modeling ability can be alleviated given a high-quality and long-contextualized debiasing corpus.
The effectiveness of task-agnostic debiasing hinges on the quantitative bias level of both the task-specific data used for downstream applications and the debiased model.
We propose a novel framework which can Propagate Socially-fair Debiasing to Downstream Fine-tuning, ProSocialTuning.
arXiv Detail & Related papers (2024-06-06T15:11:11Z) - DeNetDM: Debiasing by Network Depth Modulation [5.886480123226503]
We introduce DeNetDM, a novel debiasing method based on the observation that shallow neural networks prioritize learning core attributes, while deeper ones emphasize biases when tasked with acquiring distinct information.
Our approach effectively harnesses the diversity of bias-conflicting points within the data, surpassing previous methods and obviating the need for explicit augmentation-based methods to enhance the diversity of such bias-conflicting points.
arXiv Detail & Related papers (2024-03-28T22:17:19Z) - MAPPING: Debiasing Graph Neural Networks for Fair Node Classification
with Limited Sensitive Information Leakage [1.8238848494579714]
We propose a novel model-agnostic debiasing framework named MAPPING for fair node classification.
Our results show that MAPPING can achieve better trade-offs between utility and fairness, and privacy risks of sensitive information leakage.
arXiv Detail & Related papers (2024-01-23T14:59:46Z) - Fast Model Debias with Machine Unlearning [54.32026474971696]
Deep neural networks might behave in a biased manner in many real-world scenarios.
Existing debiasing methods suffer from high costs in bias labeling or model re-training.
We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
arXiv Detail & Related papers (2023-10-19T08:10:57Z) - Delving into Identify-Emphasize Paradigm for Combating Unknown Bias [52.76758938921129]
We propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy.
We also propose gradient alignment (GA) to balance the contributions of the mined bias-aligned and bias-conflicting samples.
Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases.
arXiv Detail & Related papers (2023-02-22T14:50:24Z) - Unbiased Supervised Contrastive Learning [10.728852691100338]
In this work, we tackle the problem of learning representations that are robust to biases.
We first present a margin-based theoretical framework that allows us to clarify why recent contrastive losses can fail when dealing with biased data.
We derive a novel formulation of the supervised contrastive loss (epsilon-SupInfoNCE), providing more accurate control of the minimal distance between positive and negative samples.
Thanks to our theoretical framework, we also propose FairKL, a new debiasing regularization loss, that works well even with extremely biased data.
arXiv Detail & Related papers (2022-11-10T13:44:57Z) - Self-supervised debiasing using low rank regularization [59.84695042540525]
Spurious correlations can cause strong biases in deep neural networks, impairing generalization ability.
We propose a self-supervised debiasing framework potentially compatible with unlabeled samples.
Remarkably, the proposed debiasing framework significantly improves the generalization performance of self-supervised learning baselines.
arXiv Detail & Related papers (2022-10-11T08:26:19Z) - D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling
Algorithmic Bias [57.87117733071416]
We propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases.
A user can detect the presence of bias against a group by identifying unfair causal relationships in the causal network.
For each interaction, say weakening/deleting a biased causal edge, the system uses a novel method to simulate a new (debiased) dataset.
arXiv Detail & Related papers (2022-08-10T03:41:48Z) - Debiasing Neural Retrieval via In-batch Balancing Regularization [25.941718123899356]
We develop a differentiable textitnormed Pairwise Ranking Fairness (nPRF) and leverage the T-statistics on top of nPRF to improve fairness.
Our method with nPRF achieves significantly less bias with minimal degradation in ranking performance compared with the baseline.
arXiv Detail & Related papers (2022-05-18T22:57:15Z) - Fairness via Representation Neutralization [60.90373932844308]
We propose a new mitigation technique, namely, Representation Neutralization for Fairness (RNF)
RNF achieves that fairness by debiasing only the task-specific classification head of DNN models.
Experimental results over several benchmark datasets demonstrate our RNF framework to effectively reduce discrimination of DNN models.
arXiv Detail & Related papers (2021-06-23T22:26:29Z)
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.