SU\G(𝔸)/K·U
Sign Up for free Log In

Author Description

Login to generate an author description

Ask a Question About This Mathematician

Tackling Algorithmic Disability Discrimination in the Hiring Process: An Ethical, Legal and Technical Analysis

2022-06-20
Maarten Buyl , Christina Cociancig , Cristina Frattone +1 more
Tackling algorithmic discrimination against persons with disabilities (PWDs) demands a distinctive approach that is fundamentally different to that applied to other protected characteristics, due to particular ethical, legal, and technical … Tackling algorithmic discrimination against persons with disabilities (PWDs) demands a distinctive approach that is fundamentally different to that applied to other protected characteristics, due to particular ethical, legal, and technical challenges. We address these challenges specifically in the context of artificial intelligence (AI) systems used in hiring processes (or automated hiring systems, AHSs), in which automated assessment procedures are subject to unique ethical and legal considerations and have an undeniable adverse impact on PWDs. In this paper, we discuss concerns and opportunities raised by AI-driven hiring in relation to disability discrimination. Ultimately, we aim to encourage further research into this topic. Hence, we establish some starting points and design a roadmap for ethicists, lawmakers, advocates as well as AI practitioners alike.
View PDF Chat

DeBayes: a Bayesian Method for Debiasing Network Embeddings

2020-01-01
Maarten Buyl , Tijl De Bie
As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their … As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their age, gender, race or other sensitive traits. In recent years much progress has been made on ensuring fairness and reducing bias in standard machine learning settings. Yet, for network embedding, with applications in vulnerable domains ranging from social network analysis to recommender systems, current options remain limited both in number and performance. We thus propose DeBayes: a conceptually elegant Bayesian method that is capable of learning debiased embeddings by using a biased prior. Our experiments show that these representations can then be used to perform link prediction that is significantly more fair in terms of popular metrics such as demographic parity and equalized opportunity.

The KL-Divergence Between a Graph Model and its Fair I-Projection as a Fairness Regularizer

2021-01-01
Maarten Buyl , Tijl De Bie
View PDF Chat

Inherent Limitations of AI Fairness

2024-01-18
Maarten Buyl , Tijl De Bie
As the real-world impact of Artificial Intelligence (AI) systems has been steadily growing, so too have these systems come under increasing scrutiny. In response, the study of AI fairness has … As the real-world impact of Artificial Intelligence (AI) systems has been steadily growing, so too have these systems come under increasing scrutiny. In response, the study of AI fairness has rapidly developed into a rich field of research with links to computer science, social science, law, and philosophy. Many technical solutions for measuring and achieving AI fairness have been proposed, yet their approach has been criticized in recent years for being misleading, unrealistic and harmful. In our paper, we survey these criticisms of AI fairness and identify key limitations that are inherent to the prototypical paradigm of AI fairness. By carefully outlining the extent to which technical solutions can realistically help in achieving AI fairness, we aim to provide the background necessary to form a nuanced opinion on developments in fair AI. This delineation also provides research opportunities for non-AI solutions peripheral to AI systems in supporting fair decision processes.
View PDF Chat

DeBayes: a Bayesian method for debiasing network embeddings

2020-07-12
Maarten Buyl , Tijl De Bie
As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their … As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their age, gender, race or other sensitive traits. In recent years much progress has been made on ensuring fairness and reducing bias in standard machine learning settings. Yet, for network embedding, with applications in vulnerable domains ranging from social network analysis to recommender systems, current options remain limited both in number and performance. We thus propose DeBayes: a conceptually elegant Bayesian method that is capable of learning debiased embeddings by using a biased prior. Our experiments show that these representations can then be used to perform link prediction that is significantly more fair in terms of popular metrics such as demographic parity and equalized opportunity.

RankFormer: Listwise Learning-to-Rank Using Listwide Labels

2023-08-04
Maarten Buyl , Paul Missault , Pierre-Antoine Sondag
Web applications where users are presented with a limited selection of items have long employed ranking models to put the most relevant results first. Any feedback received from users is … Web applications where users are presented with a limited selection of items have long employed ranking models to put the most relevant results first. Any feedback received from users is typically assumed to reflect a relative judgement on the utility of items, e.g. a user clicking on an item only implies it is better than items not clicked in the same ranked list. Hence, the objectives optimized in Learning-to-Rank (LTR) tend to be pairwise or listwise. Yet, by only viewing feedback as relative, we neglect the user's absolute feedback on the list's overall quality, e.g. when no items in the selection are clicked. We thus reconsider the standard LTR paradigm and argue the benefits of learning from this listwide signal. To this end, we propose the RankFormer as an architecture that, with a Transformer at its core, can jointly optimize a novel listwide assessment objective and a traditional listwise LTR objective. We simulate implicit feedback on public datasets and observe that the RankFormer succeeds in benefitting from listwide signals. Additionally, we conduct experiments in e-commerce on Amazon Search data and find the RankFormer to be superior to all baselines offline. An online experiment shows that knowledge distillation can be used to find immediate practical use for the RankFormer.
View PDF Chat

Large Language Models Reflect the Ideology of their Creators

2024-10-24
Maarten Buyl , Alexander Rogiers , Sander Noels +7 more
Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become … Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become popular in artificial intelligence (AI) assistants like ChatGPT and already play an influential role in how humans access information. However, the behavior of LLMs varies depending on their design, training, and use. In this paper, we uncover notable diversity in the ideological stance exhibited across different LLMs and languages in which they are accessed. We do this by prompting a diverse panel of popular LLMs to describe a large number of prominent and controversial personalities from recent world history, both in English and in Chinese. By identifying and analyzing moral assessments reflected in the generated descriptions, we find consistent normative differences between how the same LLM responds in Chinese compared to English. Similarly, we identify normative disagreements between Western and non-Western LLMs about prominent actors in geopolitical conflicts. Furthermore, popularly hypothesized disparities in political goals among Western models are reflected in significant normative differences related to inclusion, social inequality, and political scandals. Our results show that the ideological stance of an LLM often reflects the worldview of its creators. This raises important concerns around technological and regulatory efforts with the stated aim of making LLMs ideologically `unbiased', and it poses risks for political instrumentalization.
View PDF Chat

Optimal Transport of Classifiers to Fairness

2022-01-01
Maarten Buyl , Tijl De Bie
In past work on fairness in machine learning, the focus has been on forcing the prediction of classifiers to have similar statistical properties for people of different demographics. To reduce … In past work on fairness in machine learning, the focus has been on forcing the prediction of classifiers to have similar statistical properties for people of different demographics. To reduce the violation of these properties, fairness methods usually simply rescale the classifier scores, ignoring similarities and dissimilarities between members of different groups. Yet, we hypothesize that such information is relevant in quantifying the unfairness of a given classifier. To validate this hypothesis, we introduce Optimal Transport to Fairness (OTF), a method that quantifies the violation of fairness constraints as the smallest Optimal Transport cost between a probabilistic classifier and any score function that satisfies these constraints. For a flexible class of linear fairness constraints, we construct a practical way to compute OTF as a differentiable fairness regularizer that can be added to any standard classification setting. Experiments show that OTF can be used to achieve an improved trade-off between predictive power and fairness.

fairret: a Framework for Differentiable Fairness Regularization Terms

2023-01-01
Maarten Buyl , MaryBeth Defrance , Tijl De Bie
Current tools for machine learning fairness only admit a limited range of fairness definitions and have seen little integration with automatic differentiation libraries, despite the central role these libraries play … Current tools for machine learning fairness only admit a limited range of fairness definitions and have seen little integration with automatic differentiation libraries, despite the central role these libraries play in modern machine learning pipelines. We introduce a framework of fairness regularization terms (fairrets) which quantify bias as modular objectives that are easily integrated in automatic differentiation pipelines. By employing a general definition of fairness in terms of linear-fractional statistics, a wide class of fairrets can be computed efficiently. Experiments show the behavior of their gradients and their utility in enforcing fairness with minimal loss of predictive power compared to baselines. Our contribution includes a PyTorch implementation of the fairret framework.
View PDF Chat

The KL-Divergence between a Graph Model and its Fair I-Projection as a Fairness Regularizer

2021-03-02
Maarten Buyl , Tijl De Bie
Learning and reasoning over graphs is increasingly done by means of probabilistic models, e.g. exponential random graph models, graph embedding models, and graph neural networks. When graphs are modeling relations … Learning and reasoning over graphs is increasingly done by means of probabilistic models, e.g. exponential random graph models, graph embedding models, and graph neural networks. When graphs are modeling relations between people, however, they will inevitably reflect biases, prejudices, and other forms of inequity and inequality. An important challenge is thus to design accurate graph modeling approaches while guaranteeing fairness according to the specific notion of fairness that the problem requires. Yet, past work on the topic remains scarce, is limited to debiasing specific graph modeling methods, and often aims to ensure fairness in an indirect manner. We propose a generic approach applicable to most probabilistic graph modeling approaches. Specifically, we first define the class of fair graph models corresponding to a chosen set of fairness criteria. Given this, we propose a fairness regularizer defined as the KL-divergence between the graph model and its I-projection onto the set of fair models. We demonstrate that using this fairness regularizer in combination with existing graph modeling approaches efficiently trades-off fairness with accuracy, whereas the state-of-the-art models can only make this trade-off for the fairness criterion that they were specifically designed for.

The KL-Divergence between a Graph Model and its Fair I-Projection as a Fairness Regularizer

2021-01-01
Maarten Buyl , Tijl De Bie
Learning and reasoning over graphs is increasingly done by means of probabilistic models, e.g. exponential random graph models, graph embedding models, and graph neural networks. When graphs are modeling relations … Learning and reasoning over graphs is increasingly done by means of probabilistic models, e.g. exponential random graph models, graph embedding models, and graph neural networks. When graphs are modeling relations between people, however, they will inevitably reflect biases, prejudices, and other forms of inequity and inequality. An important challenge is thus to design accurate graph modeling approaches while guaranteeing fairness according to the specific notion of fairness that the problem requires. Yet, past work on the topic remains scarce, is limited to debiasing specific graph modeling methods, and often aims to ensure fairness in an indirect manner. We propose a generic approach applicable to most probabilistic graph modeling approaches. Specifically, we first define the class of fair graph models corresponding to a chosen set of fairness criteria. Given this, we propose a fairness regularizer defined as the KL-divergence between the graph model and its I-projection onto the set of fair models. We demonstrate that using this fairness regularizer in combination with existing graph modeling approaches efficiently trades-off fairness with accuracy, whereas the state-of-the-art models can only make this trade-off for the fairness criterion that they were specifically designed for.
View PDF Chat

Exploring the Performance of Continuous-Time Dynamic Link Prediction Algorithms

2024-04-22
R. Romero , Maarten Buyl , Tijl De Bie +1 more
Dynamic Link Prediction (DLP) addresses the prediction of future links in evolving networks. However, accurately portraying the performance of DLP algorithms poses challenges that might impede progress in the field. … Dynamic Link Prediction (DLP) addresses the prediction of future links in evolving networks. However, accurately portraying the performance of DLP algorithms poses challenges that might impede progress in the field. Importantly, common evaluation pipelines usually calculate ranking or binary classification metrics, where the scores of observed interactions (positives) are compared with those of randomly generated ones (negatives). However, a single metric is not sufficient to fully capture the differences between DLP algorithms, and is prone to overly optimistic performance evaluation. Instead, an in-depth evaluation should reflect performance variations across different nodes, edges, and time segments. In this work, we contribute tools to perform such a comprehensive evaluation. (1) We propose Birth–Death diagrams, a simple but powerful visualization technique that illustrates the effect of time-based train–test splitting on the difficulty of DLP on a given dataset. (2) We describe an exhaustive taxonomy of negative sampling methods that can be used at evaluation time. (3) We carry out an empirical study of the effect of the different negative sampling strategies. Our comparison between heuristics and state-of-the-art memory-based methods on various real-world datasets confirms a strong effect of using different negative sampling strategies on the test area under the curve (AUC). Moreover, we conduct a visual exploration of the prediction, with additional insights on which different types of errors are prominent over time.
View PDF Chat

KamerRaad: Enhancing Information Retrieval in Belgian National Politics through Hierarchical Summarization and Conversational Interfaces

2024-04-22
Alexander Rogiers , Maarten Buyl , Bo Seung Kang +1 more
KamerRaad is an AI tool that leverages large language models to help citizens interactively engage with Belgian political information. The tool extracts and concisely summarizes key excerpts from parliamentary proceedings, … KamerRaad is an AI tool that leverages large language models to help citizens interactively engage with Belgian political information. The tool extracts and concisely summarizes key excerpts from parliamentary proceedings, followed by the potential for interaction based on generative AI that allows users to steadily build up their understanding. KamerRaad's front-end, built with Streamlit, facilitates easy interaction, while the back-end employs open-source models for text embedding and generation to ensure accurate and relevant responses. By collecting feedback, we intend to enhance the relevancy of our source retrieval and the quality of our summarization, thereby enriching the user experience with a focus on source-driven dialogue.
View PDF Chat

ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methods

2024-09-25
MaryBeth Defrance , Maarten Buyl , Tijl De Bie
Numerous methods have been implemented that pursue fairness with respect to sensitive features by mitigating biases in machine learning. Yet, the problem settings that each method tackles vary significantly, including … Numerous methods have been implemented that pursue fairness with respect to sensitive features by mitigating biases in machine learning. Yet, the problem settings that each method tackles vary significantly, including the stage of intervention, the composition of sensitive features, the fairness notion, and the distribution of the output. Even in binary classification, these subtle differences make it highly complicated to benchmark fairness methods, as their performance can strongly depend on exactly how the bias mitigation problem was originally framed. Hence, we introduce ABCFair, a benchmark approach which allows adapting to the desiderata of the real-world problem setting, enabling proper comparability between methods for any use case. We apply ABCFair to a range of pre-, in-, and postprocessing methods on both large-scale, traditional datasets and on a dual label (biased and unbiased) dataset to sidestep the fairness-accuracy trade-off.
View PDF Chat

Persuasion with Large Language Models: a Survey

2024-11-11
Alexander Rogiers , Sander Noels , Maarten Buyl +1 more
The rapid rise of Large Language Models (LLMs) has created new disruptive possibilities for persuasive communication, by enabling fully-automated personalized and interactive content generation at an unprecedented scale. In this … The rapid rise of Large Language Models (LLMs) has created new disruptive possibilities for persuasive communication, by enabling fully-automated personalized and interactive content generation at an unprecedented scale. In this paper, we survey the research field of LLM-based persuasion that has emerged as a result. We begin by exploring the different modes in which LLM Systems are used to influence human attitudes and behaviors. In areas such as politics, marketing, public health, e-commerce, and charitable giving, such LLM Systems have already achieved human-level or even super-human persuasiveness. We identify key factors influencing their effectiveness, such as the manner of personalization and whether the content is labelled as AI-generated. We also summarize the experimental designs that have been used to evaluate progress. Our survey suggests that the current and future potential of LLM-based persuasion poses profound ethical and societal risks, including the spread of misinformation, the magnification of biases, and the invasion of privacy. These risks underscore the urgent need for ethical guidelines and updated regulatory frameworks to avoid the widespread deployment of irresponsible and harmful LLM Systems.
View PDF Chat

Persuasion with Large Language Models: a Survey

2024-11-11
Alexander Rogiers , Sander Noels , Maarten Buyl +1 more
The rapid rise of Large Language Models (LLMs) has created new disruptive possibilities for persuasive communication, by enabling fully-automated personalized and interactive content generation at an unprecedented scale. In this … The rapid rise of Large Language Models (LLMs) has created new disruptive possibilities for persuasive communication, by enabling fully-automated personalized and interactive content generation at an unprecedented scale. In this paper, we survey the research field of LLM-based persuasion that has emerged as a result. We begin by exploring the different modes in which LLM Systems are used to influence human attitudes and behaviors. In areas such as politics, marketing, public health, e-commerce, and charitable giving, such LLM Systems have already achieved human-level or even super-human persuasiveness. We identify key factors influencing their effectiveness, such as the manner of personalization and whether the content is labelled as AI-generated. We also summarize the experimental designs that have been used to evaluate progress. Our survey suggests that the current and future potential of LLM-based persuasion poses profound ethical and societal risks, including the spread of misinformation, the magnification of biases, and the invasion of privacy. These risks underscore the urgent need for ethical guidelines and updated regulatory frameworks to avoid the widespread deployment of irresponsible and harmful LLM Systems.
View PDF Chat

Large Language Models Reflect the Ideology of their Creators

2024-10-24
Maarten Buyl , Alexander Rogiers , Sander Noels +7 more
Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become … Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become popular in artificial intelligence (AI) assistants like ChatGPT and already play an influential role in how humans access information. However, the behavior of LLMs varies depending on their design, training, and use. In this paper, we uncover notable diversity in the ideological stance exhibited across different LLMs and languages in which they are accessed. We do this by prompting a diverse panel of popular LLMs to describe a large number of prominent and controversial personalities from recent world history, both in English and in Chinese. By identifying and analyzing moral assessments reflected in the generated descriptions, we find consistent normative differences between how the same LLM responds in Chinese compared to English. Similarly, we identify normative disagreements between Western and non-Western LLMs about prominent actors in geopolitical conflicts. Furthermore, popularly hypothesized disparities in political goals among Western models are reflected in significant normative differences related to inclusion, social inequality, and political scandals. Our results show that the ideological stance of an LLM often reflects the worldview of its creators. This raises important concerns around technological and regulatory efforts with the stated aim of making LLMs ideologically `unbiased', and it poses risks for political instrumentalization.
View PDF Chat

ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methods

2024-09-25
MaryBeth Defrance , Maarten Buyl , Tijl De Bie
Numerous methods have been implemented that pursue fairness with respect to sensitive features by mitigating biases in machine learning. Yet, the problem settings that each method tackles vary significantly, including … Numerous methods have been implemented that pursue fairness with respect to sensitive features by mitigating biases in machine learning. Yet, the problem settings that each method tackles vary significantly, including the stage of intervention, the composition of sensitive features, the fairness notion, and the distribution of the output. Even in binary classification, these subtle differences make it highly complicated to benchmark fairness methods, as their performance can strongly depend on exactly how the bias mitigation problem was originally framed. Hence, we introduce ABCFair, a benchmark approach which allows adapting to the desiderata of the real-world problem setting, enabling proper comparability between methods for any use case. We apply ABCFair to a range of pre-, in-, and postprocessing methods on both large-scale, traditional datasets and on a dual label (biased and unbiased) dataset to sidestep the fairness-accuracy trade-off.
View PDF Chat

Exploring the Performance of Continuous-Time Dynamic Link Prediction Algorithms

2024-04-22
R. Romero , Maarten Buyl , Tijl De Bie +1 more
Dynamic Link Prediction (DLP) addresses the prediction of future links in evolving networks. However, accurately portraying the performance of DLP algorithms poses challenges that might impede progress in the field. … Dynamic Link Prediction (DLP) addresses the prediction of future links in evolving networks. However, accurately portraying the performance of DLP algorithms poses challenges that might impede progress in the field. Importantly, common evaluation pipelines usually calculate ranking or binary classification metrics, where the scores of observed interactions (positives) are compared with those of randomly generated ones (negatives). However, a single metric is not sufficient to fully capture the differences between DLP algorithms, and is prone to overly optimistic performance evaluation. Instead, an in-depth evaluation should reflect performance variations across different nodes, edges, and time segments. In this work, we contribute tools to perform such a comprehensive evaluation. (1) We propose Birth–Death diagrams, a simple but powerful visualization technique that illustrates the effect of time-based train–test splitting on the difficulty of DLP on a given dataset. (2) We describe an exhaustive taxonomy of negative sampling methods that can be used at evaluation time. (3) We carry out an empirical study of the effect of the different negative sampling strategies. Our comparison between heuristics and state-of-the-art memory-based methods on various real-world datasets confirms a strong effect of using different negative sampling strategies on the test area under the curve (AUC). Moreover, we conduct a visual exploration of the prediction, with additional insights on which different types of errors are prominent over time.
View PDF Chat

KamerRaad: Enhancing Information Retrieval in Belgian National Politics through Hierarchical Summarization and Conversational Interfaces

2024-04-22
Alexander Rogiers , Maarten Buyl , Bo Seung Kang +1 more
KamerRaad is an AI tool that leverages large language models to help citizens interactively engage with Belgian political information. The tool extracts and concisely summarizes key excerpts from parliamentary proceedings, … KamerRaad is an AI tool that leverages large language models to help citizens interactively engage with Belgian political information. The tool extracts and concisely summarizes key excerpts from parliamentary proceedings, followed by the potential for interaction based on generative AI that allows users to steadily build up their understanding. KamerRaad's front-end, built with Streamlit, facilitates easy interaction, while the back-end employs open-source models for text embedding and generation to ensure accurate and relevant responses. By collecting feedback, we intend to enhance the relevancy of our source retrieval and the quality of our summarization, thereby enriching the user experience with a focus on source-driven dialogue.
View PDF Chat

Inherent Limitations of AI Fairness

2024-01-18
Maarten Buyl , Tijl De Bie
As the real-world impact of Artificial Intelligence (AI) systems has been steadily growing, so too have these systems come under increasing scrutiny. In response, the study of AI fairness has … As the real-world impact of Artificial Intelligence (AI) systems has been steadily growing, so too have these systems come under increasing scrutiny. In response, the study of AI fairness has rapidly developed into a rich field of research with links to computer science, social science, law, and philosophy. Many technical solutions for measuring and achieving AI fairness have been proposed, yet their approach has been criticized in recent years for being misleading, unrealistic and harmful. In our paper, we survey these criticisms of AI fairness and identify key limitations that are inherent to the prototypical paradigm of AI fairness. By carefully outlining the extent to which technical solutions can realistically help in achieving AI fairness, we aim to provide the background necessary to form a nuanced opinion on developments in fair AI. This delineation also provides research opportunities for non-AI solutions peripheral to AI systems in supporting fair decision processes.
View PDF Chat

RankFormer: Listwise Learning-to-Rank Using Listwide Labels

2023-08-04
Maarten Buyl , Paul Missault , Pierre-Antoine Sondag
Web applications where users are presented with a limited selection of items have long employed ranking models to put the most relevant results first. Any feedback received from users is … Web applications where users are presented with a limited selection of items have long employed ranking models to put the most relevant results first. Any feedback received from users is typically assumed to reflect a relative judgement on the utility of items, e.g. a user clicking on an item only implies it is better than items not clicked in the same ranked list. Hence, the objectives optimized in Learning-to-Rank (LTR) tend to be pairwise or listwise. Yet, by only viewing feedback as relative, we neglect the user's absolute feedback on the list's overall quality, e.g. when no items in the selection are clicked. We thus reconsider the standard LTR paradigm and argue the benefits of learning from this listwide signal. To this end, we propose the RankFormer as an architecture that, with a Transformer at its core, can jointly optimize a novel listwide assessment objective and a traditional listwise LTR objective. We simulate implicit feedback on public datasets and observe that the RankFormer succeeds in benefitting from listwide signals. Additionally, we conduct experiments in e-commerce on Amazon Search data and find the RankFormer to be superior to all baselines offline. An online experiment shows that knowledge distillation can be used to find immediate practical use for the RankFormer.
View PDF Chat

fairret: a Framework for Differentiable Fairness Regularization Terms

2023-01-01
Maarten Buyl , MaryBeth Defrance , Tijl De Bie
Current tools for machine learning fairness only admit a limited range of fairness definitions and have seen little integration with automatic differentiation libraries, despite the central role these libraries play … Current tools for machine learning fairness only admit a limited range of fairness definitions and have seen little integration with automatic differentiation libraries, despite the central role these libraries play in modern machine learning pipelines. We introduce a framework of fairness regularization terms (fairrets) which quantify bias as modular objectives that are easily integrated in automatic differentiation pipelines. By employing a general definition of fairness in terms of linear-fractional statistics, a wide class of fairrets can be computed efficiently. Experiments show the behavior of their gradients and their utility in enforcing fairness with minimal loss of predictive power compared to baselines. Our contribution includes a PyTorch implementation of the fairret framework.
View PDF Chat

Tackling Algorithmic Disability Discrimination in the Hiring Process: An Ethical, Legal and Technical Analysis

2022-06-20
Maarten Buyl , Christina Cociancig , Cristina Frattone +1 more
Tackling algorithmic discrimination against persons with disabilities (PWDs) demands a distinctive approach that is fundamentally different to that applied to other protected characteristics, due to particular ethical, legal, and technical … Tackling algorithmic discrimination against persons with disabilities (PWDs) demands a distinctive approach that is fundamentally different to that applied to other protected characteristics, due to particular ethical, legal, and technical challenges. We address these challenges specifically in the context of artificial intelligence (AI) systems used in hiring processes (or automated hiring systems, AHSs), in which automated assessment procedures are subject to unique ethical and legal considerations and have an undeniable adverse impact on PWDs. In this paper, we discuss concerns and opportunities raised by AI-driven hiring in relation to disability discrimination. Ultimately, we aim to encourage further research into this topic. Hence, we establish some starting points and design a roadmap for ethicists, lawmakers, advocates as well as AI practitioners alike.
View PDF Chat

Optimal Transport of Classifiers to Fairness

2022-01-01
Maarten Buyl , Tijl De Bie
In past work on fairness in machine learning, the focus has been on forcing the prediction of classifiers to have similar statistical properties for people of different demographics. To reduce … In past work on fairness in machine learning, the focus has been on forcing the prediction of classifiers to have similar statistical properties for people of different demographics. To reduce the violation of these properties, fairness methods usually simply rescale the classifier scores, ignoring similarities and dissimilarities between members of different groups. Yet, we hypothesize that such information is relevant in quantifying the unfairness of a given classifier. To validate this hypothesis, we introduce Optimal Transport to Fairness (OTF), a method that quantifies the violation of fairness constraints as the smallest Optimal Transport cost between a probabilistic classifier and any score function that satisfies these constraints. For a flexible class of linear fairness constraints, we construct a practical way to compute OTF as a differentiable fairness regularizer that can be added to any standard classification setting. Experiments show that OTF can be used to achieve an improved trade-off between predictive power and fairness.

The KL-Divergence between a Graph Model and its Fair I-Projection as a Fairness Regularizer

2021-03-02
Maarten Buyl , Tijl De Bie
Learning and reasoning over graphs is increasingly done by means of probabilistic models, e.g. exponential random graph models, graph embedding models, and graph neural networks. When graphs are modeling relations … Learning and reasoning over graphs is increasingly done by means of probabilistic models, e.g. exponential random graph models, graph embedding models, and graph neural networks. When graphs are modeling relations between people, however, they will inevitably reflect biases, prejudices, and other forms of inequity and inequality. An important challenge is thus to design accurate graph modeling approaches while guaranteeing fairness according to the specific notion of fairness that the problem requires. Yet, past work on the topic remains scarce, is limited to debiasing specific graph modeling methods, and often aims to ensure fairness in an indirect manner. We propose a generic approach applicable to most probabilistic graph modeling approaches. Specifically, we first define the class of fair graph models corresponding to a chosen set of fairness criteria. Given this, we propose a fairness regularizer defined as the KL-divergence between the graph model and its I-projection onto the set of fair models. We demonstrate that using this fairness regularizer in combination with existing graph modeling approaches efficiently trades-off fairness with accuracy, whereas the state-of-the-art models can only make this trade-off for the fairness criterion that they were specifically designed for.

The KL-Divergence Between a Graph Model and its Fair I-Projection as a Fairness Regularizer

2021-01-01
Maarten Buyl , Tijl De Bie
View PDF Chat

The KL-Divergence between a Graph Model and its Fair I-Projection as a Fairness Regularizer

2021-01-01
Maarten Buyl , Tijl De Bie
Learning and reasoning over graphs is increasingly done by means of probabilistic models, e.g. exponential random graph models, graph embedding models, and graph neural networks. When graphs are modeling relations … Learning and reasoning over graphs is increasingly done by means of probabilistic models, e.g. exponential random graph models, graph embedding models, and graph neural networks. When graphs are modeling relations between people, however, they will inevitably reflect biases, prejudices, and other forms of inequity and inequality. An important challenge is thus to design accurate graph modeling approaches while guaranteeing fairness according to the specific notion of fairness that the problem requires. Yet, past work on the topic remains scarce, is limited to debiasing specific graph modeling methods, and often aims to ensure fairness in an indirect manner. We propose a generic approach applicable to most probabilistic graph modeling approaches. Specifically, we first define the class of fair graph models corresponding to a chosen set of fairness criteria. Given this, we propose a fairness regularizer defined as the KL-divergence between the graph model and its I-projection onto the set of fair models. We demonstrate that using this fairness regularizer in combination with existing graph modeling approaches efficiently trades-off fairness with accuracy, whereas the state-of-the-art models can only make this trade-off for the fairness criterion that they were specifically designed for.
View PDF Chat

DeBayes: a Bayesian method for debiasing network embeddings

2020-07-12
Maarten Buyl , Tijl De Bie
As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their … As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their age, gender, race or other sensitive traits. In recent years much progress has been made on ensuring fairness and reducing bias in standard machine learning settings. Yet, for network embedding, with applications in vulnerable domains ranging from social network analysis to recommender systems, current options remain limited both in number and performance. We thus propose DeBayes: a conceptually elegant Bayesian method that is capable of learning debiased embeddings by using a biased prior. Our experiments show that these representations can then be used to perform link prediction that is significantly more fair in terms of popular metrics such as demographic parity and equalized opportunity.

DeBayes: a Bayesian Method for Debiasing Network Embeddings

2020-01-01
Maarten Buyl , Tijl De Bie
As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their … As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their age, gender, race or other sensitive traits. In recent years much progress has been made on ensuring fairness and reducing bias in standard machine learning settings. Yet, for network embedding, with applications in vulnerable domains ranging from social network analysis to recommender systems, current options remain limited both in number and performance. We thus propose DeBayes: a conceptually elegant Bayesian method that is capable of learning debiased embeddings by using a biased prior. Our experiments show that these representations can then be used to perform link prediction that is significantly more fair in terms of popular metrics such as demographic parity and equalized opportunity.
Coauthor Papers Together
Tijl De Bie 13
Jefrey Lijffijt 2
Alexander Rogiers 2
Sander Noels 2
R. Romero 2
MaryBeth Defrance 2
Paul Missault 1
Alexander Rogiers 1
Iris Dominguez-Catena 1
Iman Johary 1
Pierre-Antoine Sondag 1
Alexandru-Cristian Mara 1
Bo Seung Kang 1
Cristina Frattone 1
Christina Cociancig 1
Nele Roekens 1
Edith Heiter 1