Archive
Filter by Date
Filter by Categories
Filter by Tags
2021 2022 2023 2024 accountability affirmative action AISTATS Architecture Search article bias in machine learning computers and society demographic shift differential privacy explainability explaining classifiers FAcct FAccT 2022 fair machine learning fairness global explanations HCI ICAIS ICLR icml IEEE Visualization Conference impact parity interactive search model-logic subspaces Model Explanations Multi-Task Learning needfinding NeurIPS news archives NLP paper Programming Framework Seldonian classification subspace interpretability supreme court text visualization transparency trust uncertainty estimation Variational Inference VIS
Recent Posts
-
Can public support for US presidential candidates be accurately estimated by correcting biases in social polls published on X?
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…
-
Fair Machine Learning Post Affirmative Action
The U.S. Supreme Court, in a 6-3 decision on June 29, effectively ended the use of race in college admissions. Indeed, national polls found that a plurality of Americans – 42%, according to a poll conducted by the University of Massachusetts – agree that the policy should be discontinued, while 33% support its continued use…
-
My Model is Unfair, Do People Even Care? Visual Design Affects Trust and Perceived Bias in Machine Learning
Full Abstract Machine learning technology has become ubiquitous, but, unfortunately, often exhibits bias. As a consequence, disparate stakeholders need to interact with and make informed decisions about using machine learning models in everyday systems. Visualization technology can support stakeholders in understanding and evaluating trade-offs between, for example, accuracy and fairness of models. This paper aims…
-
Towards an AI Accountability Policy
It’s a new day for AI. AI systems can assist us in writing a new web script, decide whether we should worry about that weird spot in an X-ray, and find friends on social media. AI systems help in determining recidivism risk. Music-generating AI can render novel songs by Drake and the Weekend — that…
-
AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning
Full Abstract Multi-task learning (MTL) jointly learns a set of tasks by sharing parameters among tasks. It is a promising approach for reducing storage costs while improving task accuracy for many computer vision tasks. The effective adoption of MTL faces two main challenges. The first challenge is to determine what parameters to share across tasks…
-
Equi-explanation Maps: Concise and Informative Global Summary Explanations
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…
-
ClioQuery: Interactive Query-Oriented Text Analytics for Comprehensive Investigation of Historical News Archives
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…
-
Model Explanations with Differential Privacy
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.…