1.6CLMar 10, 2021
Interpretable bias mitigation for textual data: Reducing gender bias in patient notes while maintaining classification performanceJoshua R. Minot, Nicholas Cheney, Marc Maier et al.
Medical systems in general, and patient treatment decisions and outcomes in particular, are affected by bias based on gender and other demographic elements. As language models are increasingly applied to medicine, there is a growing interest in building algorithmic fairness into processes impacting patient care. Much of the work addressing this question has focused on biases encoded in language models -- statistical estimates of the relationships between concepts derived from distant reading of corpora. Building on this work, we investigate how word choices made by healthcare practitioners and language models interact with regards to bias. We identify and remove gendered language from two clinical-note datasets and describe a new debiasing procedure using BERT-based gender classifiers. We show minimal degradation in health condition classification tasks for low- to medium-levels of bias removal via data augmentation. Finally, we compare the bias semantically encoded in the language models with the bias empirically observed in health records. This work outlines an interpretable approach for using data augmentation to identify and reduce the potential for bias in natural language processing pipelines.
21.0AISep 26, 2013
A Sound and Complete Algorithm for Learning Causal Models from Relational DataMarc Maier, Katerina Marazopoulou, David Arbour et al.
The PC algorithm learns maximally oriented causal Bayesian networks. However, there is no equivalent complete algorithm for learning the structure of relational models, a more expressive generalization of Bayesian networks. Recent developments in the theory and representation of relational models support lifted reasoning about conditional independence. This enables a powerful constraint for orienting bivariate dependencies and forms the basis of a new algorithm for learning structure. We present the relational causal discovery (RCD) algorithm that learns causal relational models. We prove that RCD is sound and complete, and we present empirical results that demonstrate effectiveness.
16.2AIFeb 18, 2013
Reasoning about Independence in Probabilistic Models of Relational DataMarc Maier, Katerina Marazopoulou, David Jensen
We extend the theory of d-separation to cases in which data instances are not independent and identically distributed. We show that applying the rules of d-separation directly to the structure of probabilistic models of relational data inaccurately infers conditional independence. We introduce relational d-separation, a theory for deriving conditional independence facts from relational models. We provide a new representation, the abstract ground graph, that enables a sound, complete, and computationally efficient method for answering d-separation queries about relational models, and we present empirical results that demonstrate effectiveness.
2.4AIJun 15, 2012
Identifying Independence in Relational ModelsMarc Maier, David Jensen
The rules of d-separation provide a framework for deriving conditional independence facts from model structure. However, this theory only applies to simple directed graphical models. We introduce relational d-separation, a theory for deriving conditional independence in relational models. We provide a sound, complete, and computationally efficient method for relational d-separation, and we present empirical results that demonstrate effectiveness.