Visual Analytics and Imaging Laboratory (VAI Lab)
Computer Science Department, Stony Brook University, NY

D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias

Abstract: The widespread adoption of algorithmic decision-making systems has brought about the necessity to interpret the reasoning behind these decisions. The majority of these systems are complex black box models, and auxiliary models are often used to approximate and then explain their behavior. However, recent research suggests that such explanations are not overly accessible to lay users with no specific expertise in machine learning and this can lead to an incorrect interpretation of the underlying model. In this paper, we show that a predictive and interactive model based on causality is inherently interpretable, does not require any auxiliary model, and allows both expert and non-expert users to understand the model comprehensively. To demonstrate our method we developed Outcome Explorer, a causality guided interactive interface, and evaluated it by conducting think-aloud sessions with three expert users and a user study with 18 non-expert users. All three expert users found our tool to be comprehensive in supporting their explanation needs while the non-expert users were able to understand the inner workings of a model easily.

Teaser: The below shows the visual interface of our D-BIAS tool:

The GUI elements are as follows: (A) The Generator panel is used to create the causal network and download the debiased dataset, (B) The Causal Network view shows the causal relations between the attributes of the data, and allows the user to inject their prior in the system, (C) The Evaluation panel is used to choose the sensitive variable, the ML model and to display different evaluation metrics.

Video: Watch it to get a quick overview:

Paper: B. Ghai, K. Mueller, "D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias," IEEE Trans. on Visualization and Computer Graphics, (to appear) 2023 PDF

Funding: NSF grant IIS 1527200, IIS 1941613, and NSF SBIR contract 1926949.