Fairness by Learning Orthogonal Disentangled Representations

Sarhan, Mhd Hasan; Navab, Nassir; Eslami, Abouzar; Albarqouni, Shadi

doi:10.1007/978-3-030-58526-6_44

Cited by 41 publications

(16 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In application to face identification, disentanglement-like methods have been proposed in clustering human faces without latent code information that contain dominant features such as as skin and hair color 233 . Though applicable in settings with unobserved protected attributes, disentanglement can also be used in conjunction with adversarial learning to enforce orthogonality constraints to force independence of protected and non-protected latent codes, similarly applied to faces 234 . In combination with federated learning, frameworks such as FedDis has been demonstrated to isolate sensitive attributes in non-i.i.d.…”

Section: Fair Representation Learning Via Disentanglementmentioning

confidence: 99%

Algorithm Fairness in AI for Medicine and Healthcare

Chen¹,

Chen²,

Lipková³

et al. 2021

Preprint

View full text Add to dashboard Cite

In the current development and deployment of many artificial intelligence (AI) systems in healthcare, algorithm fairness is a challenging problem in delivering equitable care. Recent evaluation of AI models stratified across race sub-populations have revealed enormous inequalities in how patients are diagnosed, given treatments, and billed for healthcare costs. In this perspective article, we summarize the intersectional field of fairness in machine learning through the context of current issues in healthcare, outline how algorithmic biases (e.g. -image acquisition, genetic variation, intra-observer labeling variability) arise in current clinical workflows and their resulting healthcare disparities. Lastly, we also review emerging strategies for mitigating bias via decentralized learning, disentanglement, and model explainability.

show abstract

Section: Fair Representation Learning Via Disentanglementmentioning

confidence: 99%

Algorithm Fairness in AI for Medicine and Healthcare

Chen¹,

Chen²,

Lipková³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In this work, we propose to tackle domain shifts based on the assumption that the anatomical structure in brain MRI images is similar, whereas the intensity distribution is somehow different across multiple institutions. Inspired by recent works on disentangled representations [6,19,22,25,28], we propose a novel federated method, denoted Federated Disentanglement (FedDis) and argue its suitability for medical imaging. FedDis disentangles the parameter space to shape and appearance, and only shares the shape parameters with the other distributed clients to train a domain-agnostic global model (cf.…”

Section: Introductionmentioning

confidence: 99%

FedDis: Disentangled Federated Learning for Unsupervised Brain Pathology Segmentation

Bercea¹,

Wiestler²,

Rueckert³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In recent years, data-driven machine learning (ML) methods have revolutionized the computer vision community by providing novel efficient solutions to many unsolved (medical) image analysis problems. However, due to the increasing privacy concerns and data fragmentation on many different sites, existing medical data are not fully utilized, thus limiting the potential of ML. Federated learning (FL) enables multiple parties to collaboratively train a ML model without exchanging local data. However, data heterogeneity (non-IID) among the distributed clients is yet a challenge. To this end, we propose a novel federated method, denoted Federated Disentanglement (FedDis), to disentangle the parameter space into shape and appearance, and only share the shape parameter with the clients. FedDis is based on the assumption that the anatomical structure in brain MRI images is similar across multiple institutions, and sharing the shape knowledge would be beneficial in anomaly detection. In this paper, we leverage healthy brain scans of 623 subjects from multiple sites with real data (OASIS, ADNI) in a privacypreserving fashion to learn a model of normal anatomy, that allows to segment abnormal structures. We demonstrate a superior performance of FedDis on real pathological databases containing 109 subjects; two publicly available MS Lesions (MSLUB, MSISBI), and an in-house database with MS and Glioblastoma (MSI and GBI). FedDis achieved an average dice performance of 0.38, outperforming the state-of-the-art (SOTA) auto-encoder by 42% and the SOTA federated method by 11%. Further, we illustrate that FedDis learns a shape embedding that is orthogonal to the appearance and consistent under different intensity augmentations.

show abstract

“…In another work, (Nam et al 2020) show that sample performance-based methods can be used to avoid the bias in the model. A disentanglement approach to obtain the bias invariant representation has been presented in (Sarhan et al 2020). In contrast to these other techniques, our work is focused on solving the drawback that we identify in adversarial learning framework for debiasing.…”

Section: Related Workmentioning

confidence: 99%

Gradient Based Activations for Accurate Bias-Free Learning

Kurmi¹,

Sharma²,

Vardhan³

et al. 2022

AAAI

View full text Add to dashboard Cite

Bias mitigation in machine learning models is imperative, yet challenging. While several approaches have been proposed, one view towards mitigating bias is through adversarial learning. A discriminator is used to identify the bias attributes such as gender, age or race in question. This discriminator is used adversarially to ensure that it cannot distinguish the bias attributes. The main drawback in such a model is that it directly introduces a trade-off with accuracy as the features that the discriminator deems to be sensitive for discrimination of bias could be correlated with classification. In this work we solve the problem. We show that a biased discriminator can actually be used to improve this bias-accuracy tradeoff. Specifically, this is achieved by using a feature masking approach using the discriminator's gradients. We ensure that the features favoured for the bias discrimination are de-emphasized and the unbiased features are enhanced during classification. We show that this simple approach works well to reduce bias as well as improve accuracy significantly. We evaluate the proposed model on standard benchmarks. We improve the accuracy of the adversarial methods while maintaining or even improving the unbiasness and also outperform several other recent methods.

show abstract

Fairness by Learning Orthogonal Disentangled Representations

Cited by 41 publications

References 9 publications

Algorithm Fairness in AI for Medicine and Healthcare

Algorithm Fairness in AI for Medicine and Healthcare

FedDis: Disentangled Federated Learning for Unsupervised Brain Pathology Segmentation

Gradient Based Activations for Accurate Bias-Free Learning

Contact Info

Product

Resources

About