Bias in machine learning software: why? how? what to do?

E3S web of conferences, 2023

In recent years, research into and concern over algorithmic fairness and bias in machine learning systems has grown significantly. It is vital to make sure that these systems are fair, impartial, and do not support discrimination or social injustices since machine learning algorithms are becoming more and more prevalent in decision-making processes across a variety of disciplines. This abstract gives a general explanation of the idea of algorithmic fairness, the difficulties posed by bias in machine learning systems, and different solutions to these problems. Algorithmic bias and fairness in machine learning systems are crucial issues in this regard that demand the attention of academics, practitioners, and policymakers. Building fair and unbiased machine learning systems that uphold equality and prevent discrimination requires addressing biases in training data, creating fairnessaware algorithms, encouraging transparency and interpretability, and encouraging diversity and inclusivity.

Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020

Machine learning models are increasingly being used in important decision-making software such as approving bank loans, recommending criminal sentencing, hiring employees, and so on. It is important to ensure the fairness of these models so that no discrimination is made based on protected attribute (e.g., race, sex, age) while decision making. Algorithms have been developed to measure unfairness and mitigate them to a certain extent. In this paper, we have focused on the empirical evaluation of fairness and mitigations on real-world machine learning models. We have created a benchmark of 40 top-rated models from Kaggle used for 5 different tasks, and then using a comprehensive set of fairness metrics, evaluated their fairness. Then, we have applied 7 mitigation techniques on these models and analyzed the fairness, mitigation results, and impacts on performance. We have found that some model optimization techniques result in inducing unfairness in the models. On the other hand, although there are some fairness control mechanisms in machine learning libraries, they are not documented. The mitigation algorithm also exhibit common patterns such as mitigation in the post-processing is often costly (in terms of performance) and mitigation in the pre-processing stage is preferred in most cases. We have also presented different trade-off choices of fairness mitigation decisions. Our study suggests future research directions to reduce the gap between theoretical fairness aware algorithms and the software engineering methods to leverage them in practice. CCS CONCEPTS • Software and its engineering → Software creation and management; • Computing methodologies → Machine learning.

Big Data and Cognitive Computing

One of the difficulties of artificial intelligence is to ensure that model decisions are fair and free of bias. In research, datasets, metrics, techniques, and tools are applied to detect and mitigate algorithmic unfairness and bias. This study examines the current knowledge on bias and unfairness in machine learning models. The systematic review followed the PRISMA guidelines and is registered on OSF plataform. The search was carried out between 2021 and early 2022 in the Scopus, IEEE Xplore, Web of Science, and Google Scholar knowledge bases and found 128 articles published between 2017 and 2022, of which 45 were chosen based on search string optimization and inclusion and exclusion criteria. We discovered that the majority of retrieved works focus on bias and unfairness identification and mitigation techniques, offering tools, statistical approaches, important metrics, and datasets typically used for bias experiments. In terms of the primary forms of bias, data, algorithm, and us...

Although fairness in machine learning is a fairly nascent field, its relevance to daily life is immensely understated. Seeing as the future of everything from criminal justice to credit scoring to shopping lists will be dictated by the use of sophisticated machine learning predictors, it is imperative to understand the potential harms that fundamentally exist within these models. This paper begins with a broad overview of fairness from algorithmic as well as legal frameworks. Then, a taxonomy of the relevant software packages with respect to fairness and interpretability is provided in order to help facilitate usage. To conclude, a look at both current and future solutions to issues of fairness-aware systems is presented.

2020

One of the main barriers to the broader adoption of algorithmic fairness in machine learning is the trade-off between fairness and performance of ML models: many practitioners are unwilling to sacrifice the performance of their ML model for fairness. In this paper, we show that this trade-off may not be necessary. If the algorithmic biases in an ML model are due to sampling biases in the training data, then enforcing algorithmic fairness may improve the performance of the ML model on unbiased test data. We study conditions under which enforcing algorithmic fairness helps practitioners learn the Bayes decision rule for (unbiased) test data from biased training data. We also demonstrate the practical implications of our theoretical results in real-world ML tasks.

2022

Algorithms and Machine Learning (ML) are increasingly affecting everyday life and several decision-making processes, where ML has an advantage due to scalability or superior performance. Fairness in such applications is crucial, where models should not discriminate their results based on race, gender, or other protected groups. This is especially crucial for models affecting very sensitive topics, like interview hiring or recidivism prediction. Fairness is not commonly studied for regression problems compared to binary classification problems; hence, we present a simple, yet effective method based on normalisation (FaiReg), which minimises the impact of unfairness in regression problems, especially due to labelling bias. We present a theoretical analysis of the method, in addition to an empirical comparison against two standard methods for fairness, namely data balancing and adversarial training. We also include a hybrid formulation (FaiRegH), merging the presented method with data ...

Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering

Machine learning software is increasingly being used to make decisions that affect people's lives. But sometimes, the core part of this software (the learned model), behaves in a biased manner that gives undue advantages to a specific group of people (where those groups are determined by sex, race, etc.). This "algorithmic discrimination" in the AI software systems has become a matter of serious concern in the machine learning and software engineering community. There have been works done to find "algorithmic bias" or "ethical bias" in software system. Once the bias is detected in the AI software system, mitigation of bias is extremely important. In this work, we a) explain how ground truth bias in training data affects machine learning model fairness and how to find that bias in AI software, b) propose a method Fairway which combines preprocessing and in-processing approach to remove ethical bias from training data and trained model. Our results show that we can find bias and mitigate bias in a learned model, without much damaging the predictive performance of that model. We propose that (1) testing for bias and (2) bias mitigation should be a routine part of the machine learning software development life cycle. Fairway offers much support for these two purposes.

Proceedings of the Conference on Fairness, Accountability, and Transparency - FAT* '19, 2019

Computers are increasingly used to make decisions that have significant impact in people's lives. Often, these predictions can affect different population subgroups disproportionately. As a result, the issue of fairness has received much recent interest, and a number of fairness-enhanced classifiers and predictors have appeared in the literature. This paper seeks to study the following questions: how do these different techniques fundamentally compare to one another, and what accounts for the differences? Specifically, we seek to bring attention to many under-appreciated aspects of such fairness-enhancing interventions. Concretely, we present the results of an open benchmark we have developed that lets us compare a number of different algorithms under a variety of fairness measures, and a large number of existing datasets. We find that although different algorithms tend to prefer specific formulations of fairness preservations, many of these measures strongly correlate with one another. In addition, we find that fairness-preserving algorithms tend to be sensitive to fluctuations in dataset composition (simulated in our benchmark by varying training-test splits), indicating that fairness interventions might be more brittle than previously thought.

arXiv (Cornell University), 2018

Data-driven algorithms play a large role in decision making across a variety of industries. Increasingly, these algorithms are being used to make decisions that have significant ramifications for people's social and economic well-being, e.g. in sentencing, loan approval, and policing. Amid the proliferation of such systems there is a growing concern about their potential discriminatory impact. In particular, machine learning systems which are trained on biased data have the potential to learn and perpetuate those biases. A central challenge for practitioners is thus to determine whether their models display discriminatory bias. Here we present a case study in which we frame the issue of bias detection as a causal inference problem with observational data. We enumerate two main causes of bias, sampling bias and label bias, and we investigate the abilities of six different fairness metrics to detect each bias type. Based on these investigations, we propose a set of best practice guidelines to select the fairness metric that is most likely to detect bias if it is present. Additionally, we aim to identify the conditions in which certain fairness metrics may fail to detect bias and instead give practitioners a false belief that their biased model is making fair decisions.

IBM Journal of Research and Development, 2019

Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This paper introduces a new open source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license (https://github.com/ibm/aif360). The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms to use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms. The package includes a comprehensive set of fairness metrics for datasets and models, explanations for these metrics, and algorithms to mitigate bias in datasets and models. It also includes an interactive Web experience (https://aif360.mybluemix.net) that provides a gentle introduction to the concepts and capabilities for line-of-business users, as well as extensive documentation, usage guidance, and industry-specific tutorials to enable data scientists and practitioners to incorporate the most appropriate tool for their problem into their work products. The architecture of the package has been engineered to conform to a standard paradigm used in data science, thereby further improving usability for practitioners. Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking. A built-in testing infrastructure maintains code quality.