Search for: All records

While the CS education community has successfully incorporated tech-ethics assignments and modules into computing courses, we lack a defined process for instructional design to create these materials from scratch across the curriculum. To enable the development of such a process, we explore two research questions: (1) What specific instructional design challenges emerge when creating ethically-integrated assignments for CS courses? And (2) what strategies might overcome them? We address these questions using Research through Design, a method for critically examining design processes. Applying this method to our own process of creating ethics-integrated CS assignments yielded four key challenges: identifying an ethical context, maintaining a technical focus, eliciting both ethical and technical thinking from students, and making the assignment practical for the classroom. Further, the Research through Design approach revealed process-level insights for addressing these challenges, which can apply across the computing curriculum. This paper also serves as a case study of Research through Design for CS education, highlighting the importance of the instructional design process and the behind-the-scenes challenges and design decisions that go into tech-ethics materials. 

In social networks, a node’s position is, in and of itself, a form of social capital. Better-positioned members not only benefit from (faster) access to diverse information, but innately have more potential influence on information spread. Structural biases often arise from network formation, and can lead to significant disparities in information access based on position. Further, processes such as link recommendation can exacerbate this inequality by relying on network structure to augment connectivity. In this paper, we argue that one can understand and quantify this social capital through the lens of information flow in the network. In contrast to prior work, we consider the setting where all nodes may be sources of distinct information, and a node’s (dis)advantage takes into account its ability to access all information available on the network, not just that from a single source. We introduce three new measures of advantage (broadcast, influence, and control), which are quantified in terms of position in the network using access signatures – vectors that represent a node’s ability to share information with each other node in the network. We then consider the problem of improving equity by making interventions to increase the access of the least-advantaged nodes. Since all nodes are already sources of information in our model, we argue that edge augmentation is most appropriate for mitigating bias in the network structure, and frame a budgeted intervention problem for maximizing broadcast (minimum pairwise access) over the network. Finally, we propose heuristic strategies for selecting edge augmentations and empirically evaluate their performance on a corpus of real-world social networks. We demonstrate that a small number of interventions can not only significantly increase the broadcast measure of access for the least-advantaged nodes (over 5 times more than random), but also simultaneously improve the minimum influence. Additional analysis shows that edge augmentations targeted at improving minimum pairwise access can also dramatically shrink the gap in advantage between nodes (over ) and reduce disparities between their access signatures. 

Game-theoretic formulations of feature importance have become popular as a way to “explain” machine learning models. These methods define a cooperative game between the features of a model and distribute influence among these input elements using some form of the game’s unique Shapley values. Justification for these methods rests on two pillars: their desirable mathematical properties, and their applicability to specific motivations for explanations. We show that mathematical problems arise when Shapley values are used for feature importance, and that the solutions to mitigate these necessarily induce further complexity, such as the need for causal reasoning. We also draw on additional literature to argue that Shapley values are not a natural solution to the human-centric goals of explainability. 

While harms of allocation have been increasingly studied as part of the subfield of algorithmic fairness, harms of representation have received considerably less attention. In this paper, we formalize two notions of stereotyping and show how they manifest in later allocative harms within the machine learning pipeline. We also propose mitigation strategies and demonstrate their effectiveness on synthetic datasets. 

While harms of allocation have been increasingly studied as part of the subfield of algorithmic fairness, harms of representation have received considerably less attention. In this paper, we formalize two notions of stereotyping and show how they manifest in later allocative harms within the machine learning pipeline. We also propose mitigation strategies and demonstrate their effectiveness on synthetic datasets. 

Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can be direct (a direct influence on model outcomes) and indirect (model outcomes are influenced via proxy features). Feature influence can also be expressed in aggregate over the training or test data or locally with respect to a single point. Current research has typically focused on one of each of these dimensions. In this paper, we develop disentangled influence audits, a procedure to audit the indirect influence of features. Specifically, we show that disentangled representations provide a mechanism to identify proxy features in the dataset, while allowing an explicit computation of feature influence on either individual outcomes or aggregate-level outcomes. We show through both theory and experiments that disentangled influence audits can both detect proxy features and show, for each individual or in aggregate, which of these proxy features affects the classifier being audited the most. In this respect, our method is more powerful than existing methods for ascertaining feature influence.