EQUATE & Machine Learning Blog

Category: Transparency

Can public support for US presidential candidates be accurately estimated by correcting biases in social polls published on X?

Posted: November 05, 2024 Under: Digital Civics EQUATE Fairness Transparency By Przemyslaw Grabowicz

Thousands of social polls on X suggest that Trump is leading the election race by a landslide. While many recognize the bias in these polls, there’s an unexpected—and fascinating—twist, reminiscent of Asimov’s sci-fi. Informal political polls have grown in popularity on X, the platform formerly known as Twitter. For instance, one such poll, conducted recently … Continue reading "Can public support for US presidential candidates be accurately estimated by correcting biases in social polls published on X?"

Read More

Equi-explanation Maps: Concise and Informative Global Summary Explanations

Posted: July 18, 2022 Under: EQUATE Transparency By Tanya Chowdhury, Razieh Rahimi, James Allan

Full Abstract We attempt to summarize the model logic of a black-box classification model in order to generate concise and informative global explanations. We propose equi-explanation maps, a new explanation data-structure that presents the region of interest as a union of equi-explanation subspaces along with their explanation vectors. We then propose E-Map, a method to … Continue reading "Equi-explanation Maps: Concise and Informative Global Summary Explanations"

Read More

ClioQuery: Interactive Query-Oriented Text Analytics for Comprehensive Investigation of Historical News Archives

Posted: July 17, 2022 Under: Artificial Intelligence and Machine Learning EQUATE Natural Language Processing Social Science Transparency By Abram Handler, Narges Mahyar, Brendan O’Connor

Historians and archivists often find and analyze the occurrences of query words in newspaper archives, to help answer fundamental questions about society. But much work in text analytics focuses on helping people investigate other textual units, such as events, clusters, ranked documents, entity relationships, or thematic hierarchies. Informed by a study into the needs of … Continue reading "ClioQuery: Interactive Query-Oriented Text Analytics for Comprehensive Investigation of Historical News Archives"

Read More

Model Explanations with Differential Privacy

Posted: June 07, 2022 Under: EQUATE Privacy Transparency By Neel Patel, Reza Shokri, and Yair Zick

Full Abstract: Black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that model explanations can leak information about the data used to generate them, thus undermining data privacy. To address this issue, we propose differentially private algorithms to construct feature-based model explanations. … Continue reading "Model Explanations with Differential Privacy"

Read More

Computing Must Pay Attention to Outcomes to Achieve Equity

Posted: April 07, 2022 Under: Fairness Machine Learning ML for Healthcare Privacy Social Science Transparency By Michelle Trim

There is a push right now across ACM that is gathering momentum. This push is for increased attention to cultural competency [12] in the training of computing professionals. In fact, the CS202X: ACM/IEEE-CS/AAAI Computer Science Curricula Taskforce [4] has a knowledge area subcommittee devoted to SEP or Society, Ethics, and Professionalism [5]. This subcommittee is … Continue reading "Computing Must Pay Attention to Outcomes to Achieve Equity"

Read More

How to train models that do not propagate discrimination?

Posted: April 07, 2022 Under: Artificial Intelligence and Machine Learning Core ML EQUATE Fairness Machine Learning Social Science Transparency By Przemyslaw Grabowicz, Nicholas Perello, Aarshee Mishra

Powerful machine learning models can automatize decisions in critical areas of human lives, such as criminal pre-trial detention and hiring. These models are often trained on large datasets of historical decisions. However, past discriminatory human behavior may have tainted these decisions and datasets with discimination. Therefore, it is imperative to ask how can we ensure … Continue reading "How to train models that do not propagate discrimination?"

Read More