BiaScope: Visual Unfairness Diagnosis for Graph Embeddings

TL;DR

BiaScope is an interactive visualization tool designed to diagnose and understand unfairness in graph embeddings, aiding researchers and practitioners in detecting bias sources and improving fairness in graph-based applications.

Contribution

The paper introduces BiaScope, a novel visual tool for diagnosing unfairness in graph embeddings, developed through a design study with domain experts.

Findings

Experts find BiaScope effective in detecting unfairness

The tool helps locate unfairly embedded nodes and communities

It links embedding bias sources with graph topology for better understanding

Abstract

The issue of bias (i.e., systematic unfairness) in machine learning models has recently attracted the attention of both researchers and practitioners. For the graph mining community in particular, an important goal toward algorithmic fairness is to detect and mitigate bias incorporated into graph embeddings since they are commonly used in human-centered applications, e.g., social-media recommendations. However, simple analytical methods for detecting bias typically involve aggregate statistics which do not reveal the sources of unfairness. Instead, visual methods can provide a holistic fairness characterization of graph embeddings and help uncover the causes of observed bias. In this work, we present BiaScope, an interactive visualization tool that supports end-to-end visual unfairness diagnosis for graph embeddings. The tool is the product of a design study in collaboration with domain experts. It allows the user to (i) visually compare two embeddings with respect to fairness, (ii) locate nodes or graph communities that are unfairly embedded, and (iii) understand the source of bias by interactively linking the relevant embedding subspace with the corresponding graph topology. Experts' feedback confirms that our tool is effective at detecting and diagnosing unfairness. Thus, we envision our tool both as a companion for researchers in designing their algorithms as well as a guide for practitioners who use off-the-shelf graph embeddings.