Silva: Interactively Assessing Machine Learning Fairness Using Causality

AI Ethics, Fairness & AccountabilityAlgorithmic Transparency & AuditabilityAlgorithmic Fairness & BiasAI/ML Researchers & EngineersHCI ResearchersStatisticians & Data Scientists

Machine learning models risk encoding unfairness on the part of their developers or data sources. However, assessing fairness is challenging as analysts might misidentify sources of bias, fail to notice them, or misapply metrics. In this paper we introduce Silva, a system for exploring potential sources of unfairness in datasets or machine learning models interactively. Silva directs user attention to relationships between attributes through a global causal view, provides interactive recommendations, presents intermediate results, and visualizes metrics. We describe the implementation of Silva, identify salient design and technical challenges, and provide an evaluation of the tool in comparison to an existing fairness optimization tool.

Quick Actions

Share

Share this page

ios_share

https://hci.top/en/papers/chi/31984/2020

AdRecommended

Learn AI Coding at CodeNow

open_in_newOpen DOI Link
DOI: https://doi.org/10.1145/3313831.3376447
At a Glance

Paper Snapshot

fact_check
dataset
Source
CHI
calendar_month
Year
2020
emoji_events
Award
No award tagged
group
Authors
4 authors
sell
Subtopics
AI Ethics, Fairness & Accountability, Algorithmic Transparency & Auditability, Algorithmic Fairness & Bias
work
Professions
AI/ML Researchers & Engineers, HCI Researchers, Statisticians & Data Scientists
article
Content Status
Abstract only
hub
Related Papers
7 related papers