The generalization capacity of Multi-Task Learning (MTL) becomes limited when unrelated tasks negatively impact each other by updating shared parameters with conflicting gradients, resulting in negative transfer and a reduction in MTL accuracy compared to single-task learning (STL). Recently, there has been an increasing focus on the fairness of MTL models, necessitating the optimization of both accuracy and fairness for individual tasks. Similarly to how negative transfer affects accuracy, task-specific fairness considerations can adversely influence the fairness of other tasks when there is a conflict of fairness loss gradients among jointly learned tasks, termed bias transfer. To address both negative and bias transfer in MTL, we introduce a novel method called FairBranch. FairBranch branches the MTL model by assessing the similarity of learned parameters, grouping related tasks to mitigate negative transfer. Additionally, it incorporates fairness loss gradient conflict correction between adjoining task-group branches to address bias transfer within these task groups. Our experiments in tabular and visual MTL problems demonstrate that FairBranch surpasses state-of-the-art MTL methods in terms of both fairness and accuracy.
AI-driven decision-making can lead to discrimination against certain individuals or social groups based on protected characteristics/attributes such as race, gender, or age. The domain of fairness-aware machine learning focuses on methods and algorithms for understanding, mitigating, and accounting for bias in AI/ML models. Still, thus far, the vast majority of the proposed methods assess fairness based on a single protected attribute, e.g. only gender or race. In reality, though, human identities are multi-dimensional, and discrimination can occur based on more than one protected characteristic, leading to the so-called ``multi-dimensional discrimination'' or ``multi-dimensional fairness'' problem. While well-elaborated in legal literature, the multi-dimensionality of discrimination is less explored in the machine learning community. Recent approaches in this direction mainly follow the so-called intersectional fairness definition from the legal domain, whereas other notions like additive and sequential discrimination are less studied or not considered thus far. In this work, we overview the different definitions of multi-dimensional discrimination/fairness in the legal domain as well as how they have been transferred/ operationalized (if) in the fairness-aware machine learning domain. By juxtaposing these two domains, we draw the connections, identify the limitations, and point out open research directions.
Fairness-aware learning mainly focuses on single task learning (STL). The fairness implications of multi-task learning (MTL) have only recently been considered and a seminal approach has been proposed that considers the fairness-accuracy trade-off for each task and the performance trade-off among different tasks. Instead of a rigid fairness-accuracy trade-off formulation, we propose a flexible approach that learns how to be fair in a MTL setting by selecting which objective (accuracy or fairness) to optimize at each step. We introduce the L2T-FMT algorithm that is a teacher-student network trained collaboratively; the student learns to solve the fair MTL problem while the teacher instructs the student to learn from either accuracy or fairness, depending on what is harder to learn for each task. Moreover, this dynamic selection of which objective to use at each step for each task reduces the number of trade-off weights from 2T to T, where T is the number of tasks. Our experiments on three real datasets show that L2T-FMT improves on both fairness (12-19%) and accuracy (up to 2%) over state-of-the-art approaches.
Data-driven AI systems can lead to discrimination on the basis of protected attributes like gender or race. One reason for this behavior is the encoded societal biases in the training data (e.g., females are underrepresented), which is aggravated in the presence of unbalanced class distributions (e.g., "granted" is the minority class). State-of-the-art fairness-aware machine learning approaches focus on preserving the \emph{overall} classification accuracy while improving fairness. In the presence of class-imbalance, such methods may further aggravate the problem of discrimination by denying an already underrepresented group (e.g., \textit{females}) the fundamental rights of equal social privileges (e.g., equal credit opportunity). To this end, we propose AdaFair, a fairness-aware boosting ensemble that changes the data distribution at each round, taking into account not only the class errors but also the fairness-related performance of the model defined cumulatively based on the partial ensemble. Except for the in-training boosting of the group discriminated over each round, AdaFair directly tackles imbalance during the post-training phase by optimizing the number of ensemble learners for balanced error performance (BER). AdaFair can facilitate different parity-based fairness notions and mitigate effectively discriminatory outcomes. Our experiments show that our approach can achieve parity in terms of statistical parity, equal opportunity, and disparate mistreatment while maintaining good predictive performance for all classes.
As decision-making increasingly relies on machine learning and (big) data, the issue of fairness in data-driven AI systems is receiving increasing attention from both research and industry. A large variety of fairness-aware machine learning solutions have been proposed which propose fairness-related interventions in the data, learning algorithms and/or model outputs. However, a vital part of proposing new approaches is evaluating them empirically on benchmark datasets that represent realistic and diverse settings. Therefore, in this paper, we overview real-world datasets used for fairness-aware machine learning. We focus on tabular data as the most common data representation for fairness-aware machine learning. We start our analysis by identifying relationships among the different attributes, particularly w.r.t. protected attributes and class attributes, using a Bayesian network. For a deeper understanding of bias and fairness in the datasets, we investigate the interesting relationships using exploratory analysis.
Fairness-aware machine learning for multiple protected at-tributes (referred to as multi-fairness hereafter) is receiving increasing attention as traditional single-protected attribute approaches cannot en-sure fairness w.r.t. other protected attributes. Existing methods, how-ever, still ignore the fact that datasets in this domain are often imbalanced, leading to unfair decisions towards the minority class. Thus, solutions are needed that achieve multi-fairness,accurate predictive performance in overall, and balanced performance across the different classes.To this end, we introduce a new fairness notion,Multi-Max Mistreatment(MMM), which measures unfairness while considering both (multi-attribute) protected group and class membership of instances. To learn an MMM-fair classifier, we propose a multi-objective problem formulation. We solve the problem using a boosting approach that in-training,incorporates multi-fairness treatment in the distribution update and post-training, finds multiple Pareto-optimal solutions; then uses pseudo-weight based decision making to select optimal solution(s) among accurate, balanced, and multi-attribute fair solutions
Traditionally, clustering algorithms focus on partitioning the data into groups of similar instances. The similarity objective, however, is not sufficient in applications where a fair-representation of the groups in terms of protected attributes like gender or race, is required for each cluster. Moreover, in many applications, to make the clusters useful for the end-user, a balanced cardinality among the clusters is required. Our motivation comes from the education domain where studies indicate that students might learn better in diverse student groups and of course groups of similar cardinality are more practical e.g., for group assignments. To this end, we introduce the fair-capacitated clustering problem that partitions the data into clusters of similar instances while ensuring cluster fairness and balancing cluster cardinalities. We propose a two-step solution to the problem: i) we rely on fairlets to generate minimal sets that satisfy the fair constraint and ii) we propose two approaches, namely hierarchical clustering and partitioning-based clustering, to obtain the fair-capacitated clustering. The hierarchical approach embeds the additional cardinality requirements during the merging step while the partitioning-based one alters the assignment step using a knapsack problem formulation to satisfy the additional requirements. Our experiments on four educational datasets show that our approaches deliver well-balanced clusters in terms of both fairness and cardinality while maintaining a good clustering quality.
Fact checking is an essential challenge when combating fake news. Identifying documents that agree or disagree with a particular statement (claim) is a core task in this process. In this context, stance detection aims at identifying the position (stance) of a document towards a claim. Most approaches address this task through a 4-class classification model where the class distribution is highly imbalanced. Therefore, they are particularly ineffective in detecting the minority classes (for instance, 'disagree'), even though such instances are crucial for tasks such as fact-checking by providing evidence for detecting false claims. In this paper, we exploit the hierarchical nature of stance classes, which allows us to propose a modular pipeline of cascading binary classifiers, enabling performance tuning on a per step and class basis. We implement our approach through a combination of neural and traditional classification models that highlight the misclassification costs of minority classes. Evaluation results demonstrate state-of-the-art performance of our approach and its ability to significantly improve the classification performance of the important 'disagree' class.