An official website of the United States government
With the rise of AI, algorithms have become better at learning underlying patterns from the training data including ingrained social biases based on gender, race, etc. Deployment of such algorithms to domains such as hiring, healthcare, law enforcement, etc. has raised serious concerns about fairness, accountability, trust and interpretability in machine learning algorithms. To alleviate this problem, we propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases from tabular datasets. It uses a graphical causal model to represent causal relationships among different features in the dataset and as a medium to inject domain knowledge. A user can detect the presence of bias against a group, say females, or a subgroup, say black females, by identifying unfair causal relationships in the causal network and using an array of fairness metrics. Thereafter, the user can mitigate bias by refining the causal model and acting on the unfair causal edges. For each interaction, say weakening/deleting a biased causal edge, the system uses a novel method to simulate a new (debiased) dataset based on the current causal model while ensuring a minimal change from the original dataset. Users can visually assess the impact of their interactions on different fairness metrics, utility metrics, data distortion, and the underlying data distribution. Once satisfied, they can download the debiased dataset and use it for any downstream application for fairer predictions. We evaluate D-BIAS by conducting experiments on 3 datasets and also a formal user study. We found that D-BIAS helps reduce bias significantly compared to the baseline debiasing approach across different fairness metrics while incurring little data distortion and a small loss in utility. Moreover, our human-in-the-loop based approach significantly outperforms an automated approach on trust, interpretability and accountability.
more »
« less
A Formative Study of Interactive Bias Metrics in Visual Analytics Using Anchoring Bias
Interaction is the cornerstone of how people perform tasks and gain insight in visual analytics. However, people’s inherent cognitive biases impact their behavior and decision making during their interactive visual analytic process. Understanding how bias impacts the visual analytic process, how it can be measured, and how its negative effects can be mitigated is a complex problem space. Nonetheless, recent work has begun to approach this problem by proposing theoretical computational metrics that are applied to user interaction sequences to measure bias in real-time. In this paper, we implement and apply these computational metrics in the context of anchoring bias. We present the results of a formative study examining how the metrics can capture anchoring bias in real-time during a visual analytic task. We present lessons learned in the form of considerations for applying the metrics in a visual analytic tool. Our findings suggest that these computational metrics are a promising approach for characterizing bias in users’ interactive behaviors.
more »
« less
- Award ID(s):
- 1813281
- PAR ID:
- 10156426
- Date Published:
- Journal Name:
- Human-Computer Interaction – INTERACT
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Visual analytics systems enable highly interactive exploratory data analysis. Across a range of fields, these technologies have been successfully employed to help users learn from complex data. However, these same exploratory visualization techniques make it easy for users to discover spurious findings. This paper proposes new methods to monitor a user’s analytic focus during visual analysis of structured datasets and use it to surface relevant articles that contextualize the visualized findings. Motivated by interactive analyses of electronic health data, this paper introduces a formal model of analytic focus, a computational approach to dynamically update the focus model at the time of user interaction, and a prototype application that leverages this model to surface relevant medical publications to users during visual analysis of a large corpus of medical records. Evaluation results with 24 users show that the modeling approach has high levels of accuracy and is able to surface highly relevant medical abstracts.more » « less
-
Understanding how individuals focus and perform visual searches during collaborative tasks can help improve user engagement. Eye tracking measures provide informative cues for such understanding. This article presents A-DisETrac, an advanced analytic dashboard for distributed eye tracking. It uses off-the-shelf eye trackers to monitor multiple users in parallel, compute both traditional and advanced gaze measures in real-time, and display them on an interactive dashboard. Using two pilot studies, the system was evaluated in terms of user experience and utility, and compared with existing work. Moreover, the system was used to study how advanced gaze measures such as ambient-focal coefficient K and real-time index of pupillary activity relate to collaborative behavior. It was observed that the time a group takes to complete a puzzle is related to the ambient visual scanning behavior quantified and groups that spent more time had more scanning behavior. User experience questionnaire results suggest that their dashboard provides a comparatively good user experience.more » « less
-
Interactive dimensionality reduction helps analysts explore the high dimensional data based on their personal needs and domain-specific problems. Recently, expressive nonlinear models are employed to support these tasks. However, the interpretation of these human steered nonlinear models during human-in-the-loop analysis has not been explored. To address this problem, we present a new visual explanation design called semantic explanation. Semantic explanation visualizes model behaviors in a manner that is similar to users’ direct projection manipulations. This design conforms to the spatial analytic process and enables analysts better understand the updated model in response to their interactions. We propose a pipeline to empower interactive dimensionality reduction with semantic explanation using counterfactuals. Based on the pipeline, we implement a visual text analytics system with nonlinear dimensionality reduction powered by deep learning via the BERT model. We demonstrate the efficacy of semantic explanation with two case studies of academic article exploration and intelligence analysis.more » « less
-
null (Ed.)Abstract Algorithmic decision making is becoming more prevalent, increasingly impacting people’s daily lives. Recently, discussions have been emerging about the fairness of decisions made by machines. Researchers have proposed different approaches for improving the fairness of these algorithms. While these approaches can help machines make fairer decisions, they have been developed and validated on fairly clean data sets. Unfortunately, most real-world data have complexities that make them more dirty . This work considers two of these complexities by analyzing the impact of two real-world data issues on fairness—missing values and selection bias—for categorical data. After formulating this problem and showing its existence, we propose fixing algorithms for data sets containing missing values and/or selection bias that use different forms of reweighting and resampling based upon the missing value generation process. We conduct an extensive empirical evaluation on both real-world and synthetic data using various fairness metrics, and demonstrate how different missing values generated from different mechanisms and selection bias impact prediction fairness, even when prediction accuracy remains fairly constant.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
