News & Events


Controlling Bias in Artificial Intelligence

New website and resources from our <A+> Advisory Board members Elisa Celis and Nisheeth Vishnoi of Yale University. With special work on Debiasing Data, Ranking, Classification, Online Advertising, Data Summarization, Polarization and Multiwinner Voting.

The use of standard datasets, models, and algorithms often incorporates and exacerbates social biases in systems that use machine learning and artificial intelligence. Context-aware design and implementation of automated decision making algorithms is, therefore, an important and necessary venture. Our group aims to mitigate social biases in AI, with a focus on providing feasible debiased alternatives to currently-used models.

Here is the new controlling bias in artificial intelligence website

Data Summarization Prototype for gender-balanced image search.

Polarization Prototype for politically-balanced and personalized newsfeeds. Video.

Multiwinner Voting Elect a committee that is balanced across different attribute types. Deployed in Swiss elections. Video.

Ranking Prototype for gender-balanced rankings with applications to search engines, newsfeeds, and recommendation systems.

Classification Python notebook for a meta fair classification algorithm, works for various fairness metrics. Deployed in IBM AIF 360.

Online Advertising Prototype for gender-balanced and auction-based online advertising platform.

Debiasing Data Python notebook for learning and evaluating unbiased maximum-entropy distributions from biased datasets.