Exploring Text Specific and Blackbox Fairness Algorithms in Multimodal Clinical NLP

2020-11-19 · EMNLP (ClinicalNLP) 2020 11 · John Chen, Ian Berlot-Attwell, Safwan Hossain, Xindi Wang, Frank Rudzicz

Clinical machine learning is increasingly multimodal, collected in both structured tabular formats and unstructured forms such as freetext. We propose a novel task of exploring fairness on a multimodal clinical dataset, adopting equalized odds for the downstream medical prediction tasks. To this end, we investigate a modality-agnostic fairness algorithm - equalized odds post processing - and compare it to a text-specific fairness algorithm: debiased clinical word embeddings. Despite the fact that debiased word embeddings do not explicitly address equalized odds of protected groups, we show that a text-specific approach to fairness may simultaneously achieve a good balance of performance and classical notions of fairness. We hope that our paper inspires future contributions at the critical intersection of clinical NLP and fairness. The full source code is available here: https://github.com/johntiger1/multimodal_fairness

📄 PDF Abstract BibTeX arXiv:2011.09625

Code (1)

johntiger1/multimodal_fairness 공식 구현

Tasks

FairnessWord Embeddings

Imposing Consistency Properties on Blackbox Systems with Applications to SVD-Based Recommender Systems

2023-07-17 · Tung Nguyen, Jeffrey Uhlmann

In this paper we discuss pre- and post-processing methods to induce desired consistency and/or invariance properties in blackbox systems, e.g., AI-based. We demonstrate our approach in the context of blackbox SVD-based m…

Fairness Matrix Completion Recommendation Systems

On the Alignment of Group Fairness with Attribute Privacy

2022-11-18 · Jan Aalmoes, Vasisht Duddu, Antoine Boutet

Group fairness and privacy are fundamental aspects in designing trustworthy machine learning models. Previous research has highlighted conflicts between group fairness and different privacy notions. We are the first to d…

Attribute Fairness Inference Attack

On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections

2022-01-17 · ICLR Track Blog 2022 5 · Anonymous

This blog post discusses the ICLR 2021 paper "On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections" by Li et al., highlighting the importance of its theoretical results while critiquing the notions and …

Fairness Link Prediction Prediction

Blackbox Post-Processing for Multiclass Fairness

2022-01-12 · Preston Putzel, Scott Lee

Applying standard machine learning approaches for classification can produce unequal results across different demographic groups. When then used in real-world settings, these inequities can have negative societal impacts…

BIG-bench Machine Learning Binary Classification Classification Fairness

Dikaios: Privacy Auditing of Algorithmic Fairness via Attribute Inference Attacks

2022-02-04 · Jan Aalmoes, Vasisht Duddu, Antoine Boutet

Machine learning (ML) models have been deployed for high-stakes applications. Due to class imbalance in the sensitive attribute observed in the datasets, ML models are unfair on minority subgroups identified by a sensiti…