Diagnosing failures of fairness transfer across distribution shift in real-world medical settings

• URL: http://arxiv.org/abs/2202.01034v2
• Date: Fri, 10 Feb 2023 15:24:03 GMT
• Title: Diagnosing failures of fairness transfer across distribution shift in real-world medical settings
• Authors: Jessica Schrouff and Natalie Harris and Oluwasanmi Koyejo and Ibrahim Alabdulmohsin and Eva Schnider and Krista Opsahl-Ong and Alex Brown and Subhrajit Roy and Diana Mincu and Christina Chen and Awa Dieng and Yuan Liu and Vivek Natarajan and Alan Karthikesalingam and Katherine Heller and Silvia Chiappa and Alexander D'Amour
• Abstract summary: Diagnosing and mitigating changes in model fairness under distribution shift is an important component of the safe deployment of machine learning in healthcare settings. We show that this knowledge can help diagnose failures of fairness transfer, including cases where real-world shifts are more complex than is often assumed in the literature.
• Score: 60.44405686433434
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diagnosing and mitigating changes in model fairness under distribution shift is an important component of the safe deployment of machine learning in healthcare settings. Importantly, the success of any mitigation strategy strongly depends on the structure of the shift. Despite this, there has been little discussion of how to empirically assess the structure of a distribution shift that one is encountering in practice. In this work, we adopt a causal framing to motivate conditional independence tests as a key tool for characterizing distribution shifts. Using our approach in two medical applications, we show that this knowledge can help diagnose failures of fairness transfer, including cases where real-world shifts are more complex than is often assumed in the literature. Based on these results, we discuss potential remedies at each step of the machine learning pipeline.

Related papers

• Navigating Distribution Shifts in Medical Image Analysis: A Survey [23.012651270865707]
  This paper systematically reviews approaches that apply deep learning techniques to MedIA systems affected by distribution shifts. We categorize the existing body of work into Joint Training, Federated Learning, Fine-tuning, and Domain Generalization. By delving deeper into these topics, we highlight potential pathways for future research.
  arXiv  Detail & Related papers  (2024-11-05T08:01:16Z)
• Diagnostic Runtime Monitoring with Martingales [18.539691181328244]
  We present a novel framework for diagnosing distribution shifts in a streaming fashion by deploying multiple martingales simultaneously. We show that knowledge of the underlying cause of a distribution shift can lead to proper interventions over the lifecycle of a deployed system.
  arXiv  Detail & Related papers  (2024-07-31T17:05:10Z)
• FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging [68.6715007665896]
  FedMedICL is a unified framework and benchmark to holistically evaluate federated medical imaging challenges. We comprehensively evaluate several popular methods on six diverse medical imaging datasets. We find that a simple batch balancing technique surpasses advanced methods in average performance across FedMedICL experiments.
  arXiv  Detail & Related papers  (2024-07-11T19:12:23Z)
• Shifting Focus: From Global Semantics to Local Prominent Features in Swin-Transformer for Knee Osteoarthritis Severity Assessment [42.09313885494969]
  We harness the Swin Transformer's capacity to discern extended spatial dependencies within images through the hierarchical framework. Our novel contribution lies in refining local feature representations, orienting them specifically toward the final distribution of the classifier. Our model demonstrates significant robustness and precision, as evidenced by extensive validation of two established benchmarks for Knee OsteoArthritis (KOA) grade classification.
  arXiv  Detail & Related papers  (2024-03-15T01:09:58Z)
• Proxy Methods for Domain Adaptation [78.03254010884783]
  proxy variables allow for adaptation to distribution shift without explicitly recovering or modeling latent variables. We develop a two-stage kernel estimation approach to adapt to complex distribution shifts in both settings.
  arXiv  Detail & Related papers  (2024-03-12T09:32:41Z)
• Assessing Uncertainty Estimation Methods for 3D Image Segmentation under Distribution Shifts [0.36832029288386137]
  This paper explores the feasibility of using cutting-edge Bayesian and non-Bayesian methods to detect distributionally shifted samples. We compare three distinct uncertainty estimation methods, each designed to capture either unimodal or multimodal aspects in the posterior distribution. Our findings demonstrate that methods capable of addressing multimodal characteristics in the posterior distribution, offer more dependable uncertainty estimates.
  arXiv  Detail & Related papers  (2024-02-10T12:23:08Z)
• Distributionally Adaptive Meta Reinforcement Learning [85.17284589483536]
  We develop a framework for meta-RL algorithms that behave appropriately under test-time distribution shifts. Our framework centers on an adaptive approach to distributional robustness that trains a population of meta-policies to be robust to varying levels of distribution shift. We show how our framework allows for improved regret under distribution shift, and empirically show its efficacy on simulated robotics problems.
  arXiv  Detail & Related papers  (2022-10-06T17:55:09Z)
• Transferring Fairness under Distribution Shifts via Fair Consistency Regularization [15.40257564187799]
  We study how to transfer model fairness under distribution shifts, a widespread issue in practice. Inspired by the success of self-training in transferring accuracy under domain shifts, we derive a sufficient condition for transferring group fairness.
  arXiv  Detail & Related papers  (2022-06-26T06:19:56Z)
• MS Lesion Segmentation: Revisiting Weighting Mechanisms for Federated Learning [92.91544082745196]
  Federated learning (FL) has been widely employed for medical image analysis. FL's performance is limited for multiple sclerosis (MS) lesion segmentation tasks. We propose the first FL MS lesion segmentation framework via two effective re-weighting mechanisms.
  arXiv  Detail & Related papers  (2022-05-03T14:06:03Z)
• Estimating and Improving Fairness with Adversarial Learning [65.99330614802388]
  We propose an adversarial multi-task training strategy to simultaneously mitigate and detect bias in the deep learning-based medical image analysis system. Specifically, we propose to add a discrimination module against bias and a critical module that predicts unfairness within the base classification model. We evaluate our framework on a large-scale public-available skin lesion dataset.
  arXiv  Detail & Related papers  (2021-03-07T03:10:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.