اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدBias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
140
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
We present a large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples lives. We analyze the potential allocation harms that can result from semantic representation bias. To do so, we study the impact on occupation classification of including explicit gender indicators---such as first names and pronouns---in different semantic representations of online biographies. Additionally, we quantify the bias that remains when these indicators are scrubbed, and describe proxy behavior that occurs in the absence of explicit gender indicators. As we demonstrate, differences in true positive rates between genders are correlated with existing gender imbalances in occupations, which may compound these imbalances.
قيم البحث
اقرأ أيضاً
There is a growing body of work that proposes methods for mitigating bias in machine learning systems. These methods typically rely on access to protected attributes such as race, gender, or age. However, this raises two significant challenges: (1) p
rotected attributes may not be available or it may not be legal to use them, and (2) it is often desirable to simultaneously consider multiple protected attributes, as well as their intersections. In the context of mitigating bias in occupation classification, we propose a method for discouraging correlation between the predicted probability of an individuals true occupation and a word embedding of their name. This method leverages the societal biases that are encoded in word embeddings, eliminating the need for access to protected attributes. Crucially, it only requires access to individuals names at training time and not at deployment time. We evaluate two variations of our proposed method using a large-scale dataset of online biographies. We find that both variations simultaneously reduce race and gender biases, with almost no reduction in the classifiers overall true positive rate.
In recent years, AI generated art has become very popular. From generating art works in the style of famous artists like Paul Cezanne and Claude Monet to simulating styles of art movements like Ukiyo-e, a variety of creative applications have been ex
plored using AI. Looking from an art historical perspective, these applications raise some ethical questions. Can AI model artists styles without stereotyping them? Does AI do justice to the socio-cultural nuances of art movements? In this work, we take a first step towards analyzing these issues. Leveraging directed acyclic graphs to represent potential process of art creation, we propose a simple metric to quantify confounding bias due to the lack of modeling the influence of art movements in learning artists styles. As a case study, we consider the popular cycleGAN model and analyze confounding bias across various genres. The proposed metric is more effective than state-of-the-art outlier detection method in understanding the influence of art movements in artworks. We hope our work will elucidate important shortcomings of computationally modeling artists styles and trigger discussions related to accountability of AI generated art.
We present a study on predicting the factuality of reporting and bias of news media. While previous work has focused on studying the veracity of claims or documents, here we are interested in characterizing entire news media. These are under-studied
but arguably important research problems, both in their own right and as a prior for fact-checking systems. We experiment with a large list of news websites and with a rich set of features derived from (i) a sample of articles from the target news medium, (ii) its Wikipedia page, (iii) its Twitter account, (iv) the structure of its URL, and (v) information about the Web traffic it attracts. The experimental results show sizable performance gains over the baselines, and confirm the importance of each feature type.
Datasets in the Natural Sciences are often curated with the goal of aiding scientific understanding and hence may not always be in a form that facilitates the application of machine learning. In this paper, we identify three trends within the fields
of chemical reaction prediction and synthesis design that require a change in direction. First, the manner in which reaction datasets are split into reactants and reagents encourages testing models in an unrealistically generous manner. Second, we highlight the prevalence of mislabelled data, and suggest that the focus should be on outlier removal rather than data fitting only. Lastly, we discuss the problem of reagent prediction, in addition to reactant prediction, in order to solve the full synthesis design problem, highlighting the mismatch between what machine learning solves and what a lab chemist would need. Our critiques are also relevant to the burgeoning field of using machine learning to accelerate progress in experimental Natural Sciences, where datasets are often split in a biased way, are highly noisy, and contextual variables that are not evident from the data strongly influence the outcome of experiments.
Applications of machine learning (ML) to high-stakes policy settings -- such as education, criminal justice, healthcare, and social service delivery -- have grown rapidly in recent years, sparking important conversations about how to ensure fair outc
omes from these systems. The machine learning research community has responded to this challenge with a wide array of proposed fairness-enhancing strategies for ML models, but despite the large number of methods that have been developed, little empirical work exists evaluating these methods in real-world settings. Here, we seek to fill this research gap by investigating the performance of several methods that operate at different points in the ML pipeline across four real-world public policy and social good problems. Across these problems, we find a wide degree of variability and inconsistency in the ability of many of these methods to improve model fairness, but post-processing by choosing group-specific score thresholds consistently removes disparities, with important implications for both the ML research community and practitioners deploying machine learning to inform consequential policy decisions.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
