When dealing with sensitive data in automated data-driven decision-making, an important concern is to learn predictors with high performance towards a class label, whilst minimising for the discrimination towards any sensitive attribute, like gender or race, induced from biased data. A few hybrid tree optimisation criteria exist that combine classification performance and fairness. Although the threshold-free ROC-AUC is the standard for measuring traditional classification model performance, current fair tree classification methods mainly optimise for a fixed threshold on both the classification task as well as the fairness metric. In this paper, we propose a compound splitting criterion which combines threshold-free (i.e., strong) demographic parity with ROC-AUC termed SCAFF -- Splitting Criterion AUC for Fairness -- and easily extends to bagged and boosted tree frameworks. Our method simultaneously leverages multiple sensitive attributes of which the values may be multicategorical or intersectional, and is tunable with respect to the unavoidable performance-fairness trade-off. In our experiments, we demonstrate how SCAFF generates models with performance and fairness with respect to binary, multicategorical, and multiple sensitive attributes.
相關內容
Verification of probabilistic forecasts for extreme events has been a very active field of research, stirred by media and public opinions who naturally focus their attention on extreme events, and easily draw biased onclusions. In this context, classical verification methodologies tailored for extreme events, such as thresholded and weighted scoring rules, have undesirable properties that cannot be mitigated; the well-known Continuous Ranked Probability Score (CRPS) makes no exception. In this paper, we define a formal framework to assess the behavior of forecast evaluation procedures with respect to extreme events, that we use to point out that assessment based on the expectation of a proper score is not suitable for extremes. As an alternative, we propose to study the properties of the CRPS as a random variable using extreme value theory to address extreme events verification. To compare calibrated forecasts, an index is introduced that summarizes the ability of probabilistic forecasts to predict extremes. Its strengths and limitations are discussed using both theoretical arguments and simulations.
We study the problem of training a model that must obey demographic fairness conditions when the sensitive features are not available at training time -- in other words, how can we train a model to be fair by race when we don't have data about race? We adopt a fairness pipeline perspective, in which an "upstream" learner that does have access to the sensitive features will learn a proxy model for these features from the other attributes. The goal of the proxy is to allow a general "downstream" learner -- with minimal assumptions on their prediction task -- to be able to use the proxy to train a model that is fair with respect to the true sensitive features. We show that obeying multiaccuracy constraints with respect to the downstream model class suffices for this purpose, provide sample- and oracle efficient-algorithms and generalization bounds for learning such proxies, and conduct an experimental evaluation. In general, multiaccuracy is much easier to satisfy than classification accuracy, and can be satisfied even when the sensitive features are hard to predict.
Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minimax group fairness in federated learning scenarios where different participating entities may only have access to a subset of the population groups during the training phase. We formally analyze how our proposed group fairness objective differs from existing federated learning fairness criteria that impose similar performance across participants instead of demographic groups. We provide an optimization algorithm -- FedMinMax -- for solving the proposed problem that provably enjoys the performance guarantees of centralized learning algorithms. We experimentally compare the proposed approach against other state-of-the-art methods in terms of group fairness in various federated learning setups, showing that our approach exhibits competitive or superior performance.
The increasing use of machine learning in high-stakes domains -- where people's livelihoods are impacted -- creates an urgent need for interpretable and fair algorithms. In these settings it is also critical for such algorithms to be accurate. With these needs in mind, we propose a mixed integer optimization (MIO) framework for learning optimal classification trees of fixed depth that can be conveniently augmented with arbitrary domain specific fairness constraints. We benchmark our method against the state-of-the-art approach for building fair trees on popular datasets; given a fixed discrimination threshold, our approach improves out-of-sample (OOS) accuracy by 2.3 percentage points on average and obtains a higher OOS accuracy on 88.9% of the experiments. We also incorporate various algorithmic fairness notions into our method, showcasing its versatile modeling power that allows decision makers to fine-tune the trade-off between accuracy and fairness.
Federated Learning (FL) has emerged as a result of data ownership and privacy concerns to prevent data from being shared between multiple parties included in a training procedure. Although issues, such as privacy, have gained significant attention in this domain, not much attention has been given to satisfying statistical fairness measures in the FL setting. With this goal in mind, we conduct studies to show that FL is able to satisfy different fairness metrics under different data regimes consisting of different types of clients. More specifically, uncooperative or adversarial clients might contaminate the global FL model by injecting biased or poisoned models due to existing biases in their training datasets. Those biases might be a result of imbalanced training set (Zhang and Zhou 2019), historical biases (Mehrabi et al. 2021a), or poisoned data-points from data poisoning attacks against fairness (Mehrabi et al. 2021b; Solans, Biggio, and Castillo 2020). Thus, we propose a new FL framework that is able to satisfy multiple objectives including various statistical fairness metrics. Through experimentation, we then show the effectiveness of this method comparing it with various baselines, its ability in satisfying different objectives collectively and individually, and its ability in identifying uncooperative or adversarial clients and down-weighing their effect
We study the problem of inferring heterogeneous treatment effects from time-to-event data. While both the related problems of (i) estimating treatment effects for binary or continuous outcomes and (ii) predicting survival outcomes have been well studied in the recent machine learning literature, their combination -- albeit of high practical relevance -- has received considerably less attention. With the ultimate goal of reliably estimating the effects of treatments on instantaneous risk and survival probabilities, we focus on the problem of learning (discrete-time) treatment-specific conditional hazard functions. We find that unique challenges arise in this context due to a variety of covariate shift issues that go beyond a mere combination of well-studied confounding and censoring biases. We theoretically analyse their effects by adapting recent generalization bounds from domain adaptation and treatment effect estimation to our setting and discuss implications for model design. We use the resulting insights to propose a novel deep learning method for treatment-specific hazard estimation based on balancing representations. We investigate performance across a range of experimental settings and empirically confirm that our method outperforms baselines by addressing covariate shifts from various sources.
The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as TextAttack and OpenAttack. In response, there is a growing body of work on robust learning, which reduces vulnerability to these attacks, though sometimes at a high cost in compute time or accuracy. In this paper, we take an alternate approach -- we attempt to understand the attacker by analyzing adversarial text to determine which methods were used to create it. Our first contribution is an extensive dataset for attack detection and labeling: 1.5~million attack instances, generated by twelve adversarial attacks targeting three classifiers trained on six source datasets for sentiment analysis and abuse detection in English. As our second contribution, we use this dataset to develop and benchmark a number of classifiers for attack identification -- determining if a given text has been adversarially manipulated and by which attack. As a third contribution, we demonstrate the effectiveness of three classes of features for these tasks: text properties, capturing content and presentation of text; language model properties, determining which tokens are more or less probable throughout the input; and target model properties, representing how the text classifier is influenced by the attack, including internal node activations. Overall, this represents a first step towards forensics for adversarial attacks against text classifiers.
Fairness has emerged as a critical problem in federated learning (FL). In this work, we identify a cause of unfairness in FL -- \emph{conflicting} gradients with large differences in the magnitudes. To address this issue, we propose the federated fair averaging (FedFV) algorithm to mitigate potential conflicts among clients before averaging their gradients. We first use the cosine similarity to detect gradient conflicts, and then iteratively eliminate such conflicts by modifying both the direction and the magnitude of the gradients. We further show the theoretical foundation of FedFV to mitigate the issue conflicting gradients and converge to Pareto stationary solutions. Extensive experiments on a suite of federated datasets confirm that FedFV compares favorably against state-of-the-art methods in terms of fairness, accuracy and efficiency.
Developing classification algorithms that are fair with respect to sensitive attributes of the data has become an important problem due to the growing deployment of classification algorithms in various social contexts. Several recent works have focused on fairness with respect to a specific metric, modeled the corresponding fair classification problem as a constrained optimization problem, and developed tailored algorithms to solve them. Despite this, there still remain important metrics for which we do not have fair classifiers and many of the aforementioned algorithms do not come with theoretical guarantees; perhaps because the resulting optimization problem is non-convex. The main contribution of this paper is a new meta-algorithm for classification that takes as input a large class of fairness constraints, with respect to multiple non-disjoint sensitive attributes, and which comes with provable guarantees. This is achieved by first developing a meta-algorithm for a large family of classification problems with convex constraints, and then showing that classification problems with general types of fairness constraints can be reduced to those in this family. We present empirical results that show that our algorithm can achieve near-perfect fairness with respect to various fairness metrics, and that the loss in accuracy due to the imposed fairness constraints is often small. Overall, this work unifies several prior works on fair classification, presents a practical algorithm with theoretical guarantees, and can handle fairness metrics that were previously not possible.
Recently introduced generative adversarial network (GAN) has been shown numerous promising results to generate realistic samples. The essential task of GAN is to control the features of samples generated from a random distribution. While the current GAN structures, such as conditional GAN, successfully generate samples with desired major features, they often fail to produce detailed features that bring specific differences among samples. To overcome this limitation, here we propose a controllable GAN (ControlGAN) structure. By separating a feature classifier from a discriminator, the generator of ControlGAN is designed to learn generating synthetic samples with the specific detailed features. Evaluated with multiple image datasets, ControlGAN shows a power to generate improved samples with well-controlled features. Furthermore, we demonstrate that ControlGAN can generate intermediate features and opposite features for interpolated and extrapolated input labels that are not used in the training process. It implies that ControlGAN can significantly contribute to the variety of generated samples.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191