A Differentiable Distance Approximation for Fairer Image Classification
- URL: http://arxiv.org/abs/2210.04369v1
- Date: Sun, 9 Oct 2022 23:02:18 GMT
- Title: A Differentiable Distance Approximation for Fairer Image Classification
- Authors: Nicholas Rosa, Tom Drummond, Mehrtash Harandi
- Abstract summary: We propose a differentiable approximation of the variance of demographics, a metric that can be used to measure the bias, or unfairness, in an AI model.
Our approximation can be optimised alongside the regular training objective which eliminates the need for any extra models during training.
We demonstrate that our approach improves the fairness of AI models in varied task and dataset scenarios.
- Score: 31.471917430653626
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Naively trained AI models can be heavily biased. This can be particularly
problematic when the biases involve legally or morally protected attributes
such as ethnic background, age or gender. Existing solutions to this problem
come at the cost of extra computation, unstable adversarial optimisation or
have losses on the feature space structure that are disconnected from fairness
measures and only loosely generalise to fairness. In this work we propose a
differentiable approximation of the variance of demographics, a metric that can
be used to measure the bias, or unfairness, in an AI model. Our approximation
can be optimised alongside the regular training objective which eliminates the
need for any extra models during training and directly improves the fairness of
the regularised models. We demonstrate that our approach improves the fairness
of AI models in varied task and dataset scenarios, whilst still maintaining a
high level of classification accuracy. Code is available at
https://bitbucket.org/nelliottrosa/base_fairness.
Related papers
- 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) - Evaluating the Fairness of Discriminative Foundation Models in Computer
Vision [51.176061115977774]
We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP)
We then systematically evaluate existing methods for mitigating bias in these models with respect to our taxonomy.
Specifically, we evaluate OpenAI's CLIP and OpenCLIP models for key applications, such as zero-shot classification, image retrieval and image captioning.
arXiv Detail & Related papers (2023-10-18T10:32:39Z) - Boosting Fair Classifier Generalization through Adaptive Priority Reweighing [59.801444556074394]
A performance-promising fair algorithm with better generalizability is needed.
This paper proposes a novel adaptive reweighing method to eliminate the impact of the distribution shifts between training and test data on model generalizability.
arXiv Detail & Related papers (2023-09-15T13:04:55Z) - Non-Invasive Fairness in Learning through the Lens of Data Drift [88.37640805363317]
We show how to improve the fairness of Machine Learning models without altering the data or the learning algorithm.
We use a simple but key insight: the divergence of trends between different populations, and, consecutively, between a learned model and minority populations, is analogous to data drift.
We explore two strategies (model-splitting and reweighing) to resolve this drift, aiming to improve the overall conformance of models to the underlying data.
arXiv Detail & Related papers (2023-03-30T17:30:42Z) - Simultaneous Improvement of ML Model Fairness and Performance by
Identifying Bias in Data [1.76179873429447]
We propose a data preprocessing technique that can detect instances ascribing a specific kind of bias that should be removed from the dataset before training.
In particular, we claim that in the problem settings where instances exist with similar feature but different labels caused by variation in protected attributes, an inherent bias gets induced in the dataset.
arXiv Detail & Related papers (2022-10-24T13:04:07Z) - Optimising Equal Opportunity Fairness in Model Training [60.0947291284978]
Existing debiasing methods, such as adversarial training and removing protected information from representations, have been shown to reduce bias.
We propose two novel training objectives which directly optimise for the widely-used criterion of it equal opportunity, and show that they are effective in reducing bias while maintaining high performance over two classification tasks.
arXiv Detail & Related papers (2022-05-05T01:57:58Z) - Domain Adaptation meets Individual Fairness. And they get along [48.95808607591299]
We show that algorithmic fairness interventions can help machine learning models overcome distribution shifts.
In particular, we show that enforcing suitable notions of individual fairness (IF) can improve the out-of-distribution accuracy of ML models.
arXiv Detail & Related papers (2022-05-01T16:19:55Z) - Gradient Based Activations for Accurate Bias-Free Learning [22.264226961225003]
We show that a biased discriminator can actually be used to improve this bias-accuracy tradeoff.
Specifically, this is achieved by using a feature masking approach using the discriminator's gradients.
We show that this simple approach works well to reduce bias as well as improve accuracy significantly.
arXiv Detail & Related papers (2022-02-17T00:30:40Z) - Developing a novel fair-loan-predictor through a multi-sensitive
debiasing pipeline: DualFair [2.149265948858581]
We create a novel bias mitigation technique called DualFair and develop a new fairness metric (i.e. AWI) that can handle MSPSO.
We test our novel mitigation method using a comprehensive U.S mortgage lending dataset and show that our classifier, or fair loan predictor, obtains better fairness and accuracy metrics than current state-of-the-art models.
arXiv Detail & Related papers (2021-10-17T23:13:43Z) - Using Pareto Simulated Annealing to Address Algorithmic Bias in Machine
Learning [2.055949720959582]
We present a multi-objective optimisation strategy that optimises for both balanced accuracy and underestimation.
We demonstrate the effectiveness of this strategy on one synthetic and two real-world datasets.
arXiv Detail & Related papers (2021-05-31T15:51:43Z) - Addressing Fairness in Classification with a Model-Agnostic
Multi-Objective Algorithm [33.145522561104464]
The goal of fairness in classification is to learn a classifier that does not discriminate against groups of individuals based on sensitive attributes, such as race and gender.
One approach to designing fair algorithms is to use relaxations of fairness notions as regularization terms.
We leverage this property to define a differentiable relaxation that approximates fairness notions provably better than existing relaxations.
arXiv Detail & Related papers (2020-09-09T17:40:24Z)
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.