Revealing Neural Network Bias to Non-Experts Through Interactive Counterfactual Examples

Abstract

AI algorithms are not immune to biases. Traditionally, non-experts have little control in uncovering potential social bias (e.g., gender bias) in the algorithms that may impact their lives. We present a preliminary design for an interactive visualization tool CEB to reveal biases in a commonly used AI method, Neural Networks (NN). CEB combines counterfactual examples and abstraction of an NN decision process to empower non-experts to detect bias. This paper presents the design of CEB and initial findings of an expert panel (n=6) with AI, HCI, and Social science experts.

References in corpus (6)

• European Union regulations on algorithmic decision-making and a "right to explanation"
• Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes
• Counterfactual Fairness
• Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics
• Learning Not to Learn: Training Deep Neural Networks with Biased Data
• Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings

Cited by in corpus (2)

• A Survey on Interactive Reinforcement Learning: Design Principles and Open Challenges
• GAM Coach: Towards Interactive and User-centered Algorithmic Recourse