Leveraging CLIP for Inferring Sensitive Information and Improving Model Fairness

Performance disparities across sub-populations are known to exist in deep learning-based vision recognition models, but previous work has largely addressed such fairness concerns assuming knowledge of sensitive attribute labels. To overcome this reliance, previous strategies have involved separate learning structures to expose and adjust for disparities. In this work, we explore a new paradigm that does not require sensitive attribute labels, and evades the need for extra training by leveraging the vision-language model, CLIP, as a rich knowledge source to infer sensitive information. We present sample clustering based on similarity derived from image and attribute-specified language embeddings and assess their correspondence to true attribute distribution. We train a target model by re-sampling and augmenting under-performed clusters. Extensive experiments on multiple benchmark bias datasets show clear fairness gains of the model over existing baselines, which indicate that CLIP can extract discriminative sensitive information prompted by language, and used to promote model fairness.

Disparate Effect Of Missing Mediators On Transportability of Causal Effects

Transported mediation effects provide an avenue to understand how upstream interventions (such as improved neighborhood conditions like green spaces) would work differently when applied to different populations as a result of factors that mediate the effects. However, when mediators are missing in the population where the effect is to be transported, these estimates could be biased. We study this issue of missing mediators, motivated by challenges in public health, wherein mediators can be missing, not at random. We propose a sensitivity analysis framework that quantifies the impact of missing mediator data on transported mediation effects. This framework enables us to identify the settings under which the conditional transported mediation effect is rendered insignificant for the subgroup with missing mediator data. Specifically, we provide the bounds on the transported mediation effect as a function of missingness. We then apply the framework to longitudinal data from the Moving to Opportunity Study, a large-scale housing voucher experiment, to quantify the effect of missing mediators on transport effect estimates of voucher receipt, an upstream intervention on living location, in childhood on subsequent risk of mental health or substance use disorder mediated through parental health across sites. Our findings provide a tangible understanding of how much missing data can be withstood for unbiased effect estimates.

Generalization in Healthcare AI: Evaluation of a Clinical Large Language Model

Advances in large language models (LLMs) provide new opportunities in healthcare for improved patient care, clinical decision-making, and enhancement of physician and administrator workflows. However, the potential of these models importantly depends on their ability to generalize effectively across clinical environments and populations, a challenge often underestimated in early development. To better understand reasons for these challenges and inform mitigation approaches, we evaluated ClinicLLM, an LLM trained on [HOSPITAL]'s clinical notes, analyzing its performance on 30-day all-cause readmission prediction focusing on variability across hospitals and patient characteristics. We found poorer generalization particularly in hospitals with fewer samples, among patients with government and unspecified insurance, the elderly, and those with high comorbidities. To understand reasons for lack of generalization, we investigated sample sizes for fine-tuning, note content (number of words per note), patient characteristics (comorbidity level, age, insurance type, borough), and health system aspects (hospital, all-cause 30-day readmission, and mortality rates). We used descriptive statistics and supervised classification to identify features. We found that, along with sample size, patient age, number of comorbidities, and the number of words in notes are all important factors related to generalization. Finally, we compared local fine-tuning (hospital specific), instance-based augmented fine-tuning and cluster-based fine-tuning for improving generalization. Among these, local fine-tuning proved most effective, increasing AUC by 0.25% to 11.74% (most helpful in settings with limited data). Overall, this study provides new insights for enhancing the deployment of large language models in the societally important domain of healthcare, and improving their performance for broader populations.

Impact on Public Health Decision Making by Utilizing Big Data Without Domain Knowledge

New data sources, and artificial intelligence (AI) methods to extract information from them are becoming plentiful, and relevant to decision making in many societal applications. An important example is street view imagery, available in over 100 countries, and considered for applications such as assessing built environment aspects in relation to community health outcomes. 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. To study this risk, we utilize 2.02 million GSV images along with health, demographic, and socioeconomic data from New York City. Initially, we demonstrate that built environment characteristics inferred from GSV labels at the intra-city level may exhibit inadequate alignment with the ground truth. We also find that the average individual-level behavior of physical inactivity significantly mediates the impact of built environment features by census tract, as measured through GSV. Finally, using a causal framework which accounts for these mediators of environmental impacts on health, we find that altering 10% of samples in the two lowest tertiles would result in a 4.17 (95% CI 3.84 to 4.55) or 17.2 (95% CI 14.4 to 21.3) times bigger decrease on the prevalence of obesity or diabetes, than the same proportional intervention on the number of crosswalks by census tract. This work illustrates important issues of robustness and model specification for informing effective allocation of interventions using new data sources.

Understanding Disparities in Post Hoc Machine Learning Explanation

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. Accordingly, through both simulations as well as experiments on a real-world dataset, we specifically assess challenges to explanation disparities that originate from properties of the data: limited sample size, covariate shift, concept shift, omitted variable bias, and challenges based on model properties: inclusion of the sensitive attribute and appropriate functional form. Through controlled simulation analyses, our study demonstrates that increased covariate shift, concept shift, and omission of covariates increase explanation disparities, with the effect pronounced higher for neural network models that are better able to capture the underlying functional form in comparison to linear models. We also observe consistent findings regarding the effect of concept shift and omitted variable bias on explanation disparities in the Adult income dataset. Overall, results indicate that disparities in model explanations can also depend on data and model properties. Based on this systematic investigation, we provide recommendations for the design of explanation methods that mitigate undesirable disparities.

A Brief Tutorial on Sample Size Calculations for Fairness Audits

In fairness audits, a standard objective is to detect whether a given algorithm performs substantially differently between subgroups. Properly powering the statistical analysis of such audits is crucial for obtaining informative fairness assessments, as it ensures a high probability of detecting unfairness when it exists. However, limited guidance is available on the amount of data necessary for a fairness audit, lacking directly applicable results concerning commonly used fairness metrics. Additionally, the consideration of unequal subgroup sample sizes is also missing. In this tutorial, we address these issues by providing guidance on how to determine the required subgroup sample sizes to maximize the statistical power of hypothesis tests for detecting unfairness. Our findings are applicable to audits of binary classification models and multiple fairness metrics derived as summaries of the confusion matrix. Furthermore, we discuss other aspects of audit study designs that can increase the reliability of audit results.

Fair contrastive pre-training for geographic images

Contrastive representation learning is widely employed in visual recognition for geographic image data (remote-sensing such as satellite imagery or proximal sensing such as street-view imagery), but because of landscape heterogeneity, models can show disparate performance across spatial units. In this work, we consider fairness risks in land-cover semantic segmentation which uses pre-trained representation in contrastive self-supervised learning. We assess class distribution shifts and model prediction disparities across selected sensitive groups: urban and rural scenes for satellite image datasets and city GDP level for a street view image dataset. We propose a mutual information training objective for multi-level latent space. The objective improves feature identification by removing spurious representations of dense local features which are disparately distributed across groups. The method achieves improved fairness results and outperforms state-of-the-art methods in terms of precision-fairness trade-off. In addition, we validate that representations learnt with the proposed method include lowest sensitive information using a linear separation evaluation. This work highlights the need for specific fairness analyses in geographic images, and provides a solution that can be generalized to different self-supervised learning methods or image data. Our code is available at: https://anonymous.4open.science/r/FairDCL-1283

Segmenting across places: The need for fair transfer learning with satellite imagery

The increasing availability of high-resolution satellite imagery has enabled the use of machine learning to support land-cover measurement and inform policy-making. However, labelling satellite images is expensive and is available for only some locations. This prompts the use of transfer learning to adapt models from data-rich locations to others. Given the potential for high-impact applications of satellite imagery across geographies, a systematic assessment of transfer learning implications is warranted. In this work, we consider the task of land-cover segmentation and study the fairness implications of transferring models across locations. We leverage a large satellite image segmentation benchmark with 5987 images from 18 districts (9 urban and 9 rural). Via fairness metrics we quantify disparities in model performance along two axes -- across urban-rural locations and across land-cover classes. Findings show that state-of-the-art models have better overall accuracy in rural areas compared to urban areas, through unsupervised domain adaptation methods transfer learning better to urban versus rural areas and enlarge fairness gaps. In analysis of reasons for these findings, we show that raw satellite images are overall more dissimilar between source and target districts for rural than for urban locations. This work highlights the need to conduct fairness analysis for satellite imagery segmentation models and motivates the development of methods for fair transfer learning in order not to introduce disparities between places, particularly urban and rural locations.

Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty

Transparency of algorithmic systems entails exposing system properties to various stakeholders for purposes that include understanding, improving, and/or contesting predictions. The machine learning (ML) community has mostly considered explainability as a proxy for transparency. With this work, we seek to encourage researchers to study uncertainty as a form of transparency and practitioners to communicate uncertainty estimates to stakeholders. First, we discuss methods for assessing uncertainty. Then, we describe the utility of uncertainty for mitigating model unfairness, augmenting decision-making, and building trustworthy systems. We also review methods for displaying uncertainty to stakeholders and discuss how to collect information required for incorporating uncertainty into existing ML pipelines. Our contribution is an interdisciplinary review to inform how to measure, communicate, and use uncertainty as a form of transparency.