Research Papers

Graphs can facilitate modeling various complex systems such as gene networks and power grids, as well as analyzing the underlying relations within them. Learning over graphs has recently attracted increasing attention, particularly graph neural network-based (GNN) solutions, among which graph attention networks (GATs) have become one of the most widely utilized neural network structures for graph-based tasks. Although it is shown that the use of graph structures in learning results in the amplification of algorithmic bias, the influence of the attention design in GATs on algorithmic bias has not been investigated. Motivated by this, the present study first carries out a theoretical analysis in order to demonstrate the sources of algorithmic bias in GAT-based learning for node classification. Then, a novel algorithm, FairGAT, that leverages a fairness-aware attention design is developed based on the theoretical findings. Experimental results on real-world networks demonstrate that FairGAT improves group fairness measures while also providing comparable utility to the fairness-aware baselines for node classification and link prediction.

A Comparative Analysis of Bias Amplification in Graph Neural Network Approaches for Recommender Systems

Nikzad Chizari, Niloufar Shoeibi, María N. Moreno-García

Recommender Systems (RSs) are used to provide users with personalized item recommendations and help them overcome the problem of information overload. Currently, recommendation methods based on deep learning are gaining ground over traditional methods such as matrix factorization due to their ability to represent the complex relationships between users and items and to incorporate additional information. The fact that these data have a graph structure and the greater capability of Graph Neural Networks (GNNs) to learn from these structures has led to their successful incorporation into recommender systems. However, the bias amplification issue needs to be investigated while using these algorithms. Bias results in unfair decisions, which can negatively affect the company reputation and financial status due to societal disappointment and environmental harm. In this paper, we aim to comprehensively study this problem through a literature review and an analysis of the behavior against biases of different GNN-based algorithms compared to state-of-the-art methods. We also intend to explore appropriate solutions to tackle this issue with the least possible impact on the model performance.

The goal of this work is to help mitigate the already existing gender wage gap by supplying unbiased job recommendations based on resumes from job seekers. We employ a generative adversarial network to remove gender bias from word2vec representations of 12M job vacancy texts and 900k resumes. Our results show that representations created from recruitment texts contain algorithmic bias and that this bias results in real-world consequences for recommendation systems. Without controlling for bias, women are recommended jobs with significantly lower salary in our data. With adversarially fair representations, this wage gap disappears, meaning that our debiased job recommendations reduce wage discrimination. We conclude that adversarial debiasing of word representations can increase real-world fairness of systems and thus may be part of the solution for creating fairness-aware recommendation systems.

Many instances of algorithmic bias are caused by distributional shifts. For example, machine learning (ML) models often perform worse on demographic groups that are underrepresented in the training data. In this paper, we leverage this connection between algorithmic fairness and distribution shifts to show that algorithmic fairness interventions can help ML models overcome distribution shifts, and that domain adaptation methods (for overcoming distribution shifts) can mitigate algorithmic biases. In particular, we show that (i) enforcing suitable notions of individual fairness (IF) can improve the out-of-distribution accuracy of ML models under the covariate shift assumption and that (ii) it is possible to adapt representation alignment methods for domain adaptation to enforce individual fairness. The former is unexpected because IF interventions were not developed with distribution shifts in mind. The latter is also unexpected because representation alignment is not a common approach in the individual fairness literature.

In this paper, we argue that AI ethics must move beyond the concepts of race-based representation and bias, and towards those that probe the deeper relations that impact how these systems are designed, developed, and deployed. Many recent discussions on ethical considerations of bias in AI systems have centered on racial bias. We contend that antiblackness in AI requires more of an examination of the ontological space that provides a foundation for the design, development, and deployment of AI systems. We examine what this contention means from the perspective of the sociocultural context in which AI systems are designed, developed, and deployed and focus on intersections with anti-Black racism (antiblackness). To bring these multiple perspectives together and show an example of antiblackness in the face of attempts at de-biasing, we discuss results from auditing an existing open-source semantic network (ConceptNet). We use this discussion to further contextualize antiblackness in design, development, and deployment of AI systems and suggest questions one may ask when attempting to combat antiblackness in AI systems.

Machine learning algorithms are useful for various predictions tasks, but they can also learn how to discriminate, based on gender, race or other sensitive attributes. This realization gave rise to the field of fair machine learning, which aims to measure and mitigate such algorithmic bias. This manuscript describes the R-package fairadapt, which implements a causal inference pre-processing method. By making use of a causal graphical model and the observed data, the method can be used to address hypothetical questions of the form "What would my salary have been, had I been of a different gender/race?". Such individual level counterfactual reasoning can help eliminate discrimination and help justify fair decisions. We also discuss appropriate relaxations which assume certain causal pathways from the sensitive attribute to the outcome are not discriminatory.

It is widely accepted that technology is ubiquitous across the planet and has the potential to solve many of the problems existing in the Global South. Moreover, the rapid advancement of artificial intelligence (AI) brings with it the potential to address many of the challenges outlined in the Sustainable Development Goals (SDGs) in ways which were never before possible. However, there are many questions about how such advanced technologies should be managed and governed, and whether or not the emerging ethical frameworks and standards for AI are dominated by the Global North. This research examines the growing body of documentation on AI ethics to examine whether or not there is equality of participation in the ongoing global discourse. Specifically, it seeks to discover if both countries in the Global South and women are underrepresented in this discourse. Findings indicate a dearth of references to both of these themes in the AI ethics documents, suggesting that the associated ethical implications and risks are being neglected. Without adequate input from both countries in the Global South and from women, such ethical frameworks and standards may be discriminatory with the potential to reinforce marginalisation.

The idea of fairness and justice has long and deep roots in Western civilization, and is strongly linked to ethics. It is therefore not strange that it is core to the current discussion about the ethics of development and use of AI systems. In this short paper, I wish to further motivate my position in this matter: ``I will never be completely fair. Nothing ever is. The point is not complete fairness, but the need to establish metrics and thresholds for fairness that ensure trust in AI systems".

Modern software relies heavily on data and machine learning, and affects decisions that shape our world. Unfortunately, recent studies have shown that because of biases in data, software systems frequently inject bias into their decisions, from producing better closed caption transcriptions of men's voices than of women's voices to overcharging people of color for financial loans. To address bias in machine learning, data scientists need tools that help them understand the trade-offs between model quality and fairness in their specific data domains. Toward that end, we present fairkit-learn, a toolkit for helping data scientists reason about and understand fairness. Fairkit-learn works with state-of-the-art machine learning tools and uses the same interfaces to ease adoption. It can evaluate thousands of models produced by multiple machine learning algorithms, hyperparameters, and data permutations, and compute and visualize a small Pareto-optimal set of models that describe the optimal trade-offs between fairness and quality. We evaluate fairkit-learn via a user study with 54 students, showing that students using fairkit-learn produce models that provide a better balance between fairness and quality than students using scikit-learn and IBM AI Fairness 360 toolkits. With fairkit-learn, users can select models that are up to 67% more fair and 10% more accurate than the models they are likely to train with scikit-learn.

In the past decade, Artificial Intelligence (AI) has become a part of our daily lives due to major advances in Machine Learning (ML) techniques. In spite of an explosive growth in the raw AI technology and in consumer facing applications on the internet, its adoption in business applications has conspicuously lagged behind. For business/mission-critical systems, serious concerns about reliability and maintainability of AI applications remain. Due to the statistical nature of the output, software 'defects' are not well defined. Consequently, many traditional quality management techniques such as program debugging, static code analysis, functional testing, etc. have to be reevaluated. Beyond the correctness of an AI model, many other new quality attributes, such as fairness, robustness, explainability, transparency, etc. become important in delivering an AI system. The purpose of this paper is to present a view of a holistic quality management framework for ML applications based on the current advances and identify new areas of software engineering research to achieve a more trustworthy AI.

Human society had a long history of suffering from cognitive biases leading to social prejudices and mass injustice. The prevalent existence of cognitive biases in large volumes of historical data can pose a threat of being manifested as unethical and seemingly inhuman predictions as outputs of AI systems trained on such data. To alleviate this problem, we propose a bias-aware multi-objective learning framework that given a set of identity attributes (e.g. gender, ethnicity etc.) and a subset of sensitive categories of the possible classes of prediction outputs, learns to reduce the frequency of predicting certain combinations of them, e.g. predicting stereotypes such as `most blacks use abusive language', or `fear is a virtue of women'. Our experiments conducted on an emotion prediction task with balanced class priors shows that a set of baseline bias-agnostic models exhibit cognitive biases with respect to gender, such as women are prone to be afraid whereas men are more prone to be angry. In contrast, our proposed bias-aware multi-objective learning methodology is shown to reduce such biases in the predictied emotions.

SHAP-based Explanations are Sensitive to Feature Representation

Hyunseung Hwang, Andrew Bell, Joao Fonseca +3

Local feature-based explanations are a key component of the XAI toolkit. These explanations compute feature importance values relative to an ``interpretable'' feature representation. In tabular data, feature values themselves are often considered interpretable. This paper examines the impact of data engineering choices on local feature-based explanations. We demonstrate that simple, common data engineering techniques, such as representing age with a histogram or encoding race in a specific way, can manipulate feature importance as determined by popular methods like SHAP. Notably, the sensitivity of explanations to feature representation can be exploited by adversaries to obscure issues like discrimination. While the intuition behind these results is straightforward, their systematic exploration has been lacking. Previous work has focused on adversarial attacks on feature-based explainers by biasing data or manipulating models. To the best of our knowledge, this is the first study demonstrating that explainers can be misled by standard, seemingly innocuous data engineering techniques.