Related papers: Learning Fair Representations via Rate-Distortion …
Fair classification and fair representation learning are two important problems in supervised and unsupervised fair machine learning, respectively. Fair classification asks for a classifier that maximizes accuracy on a given data…
A rekindled the interest in auto-encoder algorithms has been spurred by recent work on deep learning. Current efforts have been directed towards effective training of auto-encoder architectures with a large number of coding units. Here, we…
We present the Assignment-Maximization Spectral Attribute removaL (AMSAL) algorithm, which erases information from neural representations when the information to be erased is implicit rather than directly being aligned to each input…
Traditional approaches to learning fair machine learning models often require rebuilding models from scratch, typically without considering potentially existing models. In a context where models need to be retrained frequently, this can…
We propose to learn invariant representations, in the data domain, to achieve interpretability in algorithmic fairness. Invariance implies a selectivity for high level, relevant correlations w.r.t. class label annotations, and a robustness…
In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and…
Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject to systematic…
Supervised learning systems are trained using historical data and, if the data was tainted by discrimination, they may unintentionally learn to discriminate against protected groups. We propose that fair learning methods, despite training…
To mitigate the effects of undesired biases in models, several approaches propose to pre-process the input dataset to reduce the risks of discrimination by preventing the inference of sensitive attributes. Unfortunately, most of these…
In the social sciences, it is often necessary to debias studies and surveys before valid conclusions can be drawn. Debiasing algorithms enable the computational removal of bias using sample weights. However, an issue arises when only a…
In education data mining (EDM) communities, machine learning has achieved remarkable success in discovering patterns and structures to tackle educational challenges. Notably, fairness and algorithmic bias have gained attention in learning…
One of the pursued objectives of deep learning is to provide tools that learn abstract representations of reality from the observation of multiple contextual situations. More precisely, one wishes to extract disentangled representations…
The goal of Fair Representation Learning (FRL) is to mitigate biases in machine learning models by learning data representations that enable high accuracy on downstream tasks while minimizing discrimination based on sensitive attributes.…
Decision making is a process that is extremely prone to different biases. In this paper we consider learning fair representations that aim at removing nuisance (sensitive) information from the decision process. For this purpose, we propose…
The use of language technologies in high-stake settings is increasing in recent years, mostly motivated by the success of Large Language Models (LLMs). However, despite the great performance of LLMs, they are are susceptible to ethical…
Large pre-trained vision-language models (VLMs) reduce the time for developing predictive models for various vision-grounded language downstream tasks by providing rich, adaptable image and text representations. However, these models suffer…
In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about…
Existing bias mitigation methods for DNN models primarily work on learning debiased encoders. This process not only requires a lot of instance-level annotations for sensitive attributes, it also does not guarantee that all fairness…
Explicit and implicit bias clouds human judgement, leading to discriminatory treatment of minority groups. A fundamental goal of algorithmic fairness is to avoid the pitfalls in human judgement by learning policies that improve the overall…
As machine learning is increasingly used to make real-world decisions, recent research efforts aim to define and ensure fairness in algorithmic decision making. Existing methods often assume a fixed set of observable features to define…