no code implementations • 15 Sep 2018 • Vishwali Mhasawade, Ildikó Emese Szabó, Melanie Tosik, Sheng-Fu Wang
In this work, we investigate whether the learnability bias exhibited by children is in part due to the distribution of quantifiers in natural language.
no code implementations • 21 Nov 2018 • Vishwali Mhasawade, Nabeel Abdur Rehman, Rumi Chunara
Population attributes are essential in health for understanding who the data represents and precision medicine efforts.
1 code implementation • 24 Aug 2019 • Vishwali Mhasawade, Nabeel Abdur Rehman, Rumi Chunara
Based on sources of stability in the model, we posit that for human-sourced data and health prediction tasks we can combine environment and population information in a novel population-aware hierarchical Bayesian domain adaptation framework that harnesses multiple invariant components through population attributes when needed.
no code implementations • 2 Nov 2019 • Harvineet Singh, Rina Singh, Vishwali Mhasawade, Rumi Chunara
We study the problem of learning fair prediction models for unseen test sets distributed differently from the train set.
no code implementations • 21 Jul 2020 • Vishwali Mhasawade, Yuan Zhao, Rumi Chunara
Research in population and public health focuses on the mechanisms between different cultural, social, and environmental factors and their effect on the health, of not just individuals, but communities as a whole.
no code implementations • 14 Oct 2020 • Vishwali Mhasawade, Rumi Chunara
While work in algorithmic fairness to-date has primarily focused on addressing discrimination due to individually linked attributes, social science research elucidates how some properties we link to individuals can be conceptualized as having causes at macro (e. g. structural) levels, and it may be important to be fair to attributes at multiple levels.
no code implementations • 25 Jan 2024 • Vishwali Mhasawade, Salman Rahman, Zoe Haskell-Craig, Rumi Chunara
Previous work has highlighted that existing post-hoc explanation methods exhibit disparities in explanation fidelity (across 'race' and 'gender' as sensitive attributes), and while a large body of work focuses on mitigating these issues at the explanation metric level, the role of the data generating process and black box model in relation to explanation disparities remains largely unexplored.
no code implementations • 8 Feb 2024 • Miao Zhang, Salman Rahman, Vishwali Mhasawade, Rumi Chunara
Relevant to such uses, important examples of bias in the use of AI are evident when decision-making based on data fails to account for the robustness of the data, or predictions are based on spurious correlations.
no code implementations • 13 Mar 2024 • Vishwali Mhasawade, Rumi Chunara
We study this issue of missing mediators, motivated by challenges in public health, wherein mediators can be missing, not at random.