Princeton Bias-in-AI Reading Group

We talk about bias and fairness issues that emerge in artificial intelligence.

Meets every other Tuesday 4:00-5:00pm EST. Sign up for the mailing list here (Princeton affiliates only please).

Past meetings here.

Spring 2023

2/7/23: Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization? by Bommasani et al. (NeurIPS 2022)

2/21/23: A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithms by Coston et al. (SATML 2023)

3/21/23: Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkit by Deng et al. (FAccT 2022)

4/11/23: Jury Learning: Integrating Dissenting Voices into Machine Learning Models by Gordon et al. (CHI 2022)

4/18/23: William Agnew - What is Computer Vision Used for?

5/2/23: Vikram Ramaswamy - GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition

Fall 2022

9/20/22: Angelina Wang - Model Multiplicity: Opportunities, Concerns, and Solutions by Black et al. (FAccT 2022)

10/4/22: Rose Guingrich - Gender & Conversational Agents (UNESCO paper)

10/11/22: Sayash Kapoor and Angelina Wang - Against Predictive Optimization: On the Legitimacy of Decision-Making Algorithms that Optimize Predictive Accuracy

11/15/22: Vikram V. Ramaswamy - Overlooked factors in concept-based explanations: Dataset choice, concept salience, and human capability

12/6/22: Christelle Tessono - Analyzing Canada's Proposed AI and Data Act

Organizers:

Founded by Arvind Narayanan and Olga Russakovsky in Fall 2017

AY 2021-2022: Angelina Wang

AY 2020-2021: Angelina Wang

AY 2019-2020: Felix Yu

AY 2018-2019: Haochen Li