Fair Interpretable Representation Learning with Correction Vectors

Cerrato, Mattia; Coronel, Alesia Vallenas; Köppel, Marius; Segner, Alexander; Esposito, Roberto; Krämer, Stefan

doi:10.48550/arxiv.2202.03078

Cited by 2 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) Intrinsic: Here, we restrict to include those intrinsic methods that explicitly considered fairness notions in their study [49]- [62].…”

Section: A Result-oriented Fairnessmentioning

confidence: 99%

“…Cerrato et al [49] introduced the concept of correction vectors to enhance interpretability in fair representation learning. These correction vectors can be computed explicitly, by modifying an existing neural network through the use of a Gradient Reversal Layer (GRL) to achieve interpretability.…”

Section: A Result-oriented Fairnessmentioning

confidence: 99%

“…While significant research efforts have been dedicated to fair representation learning, the aspect of interpretability remains largely unexplored. Several recent studies [49]- [55] have made strides in incorporating interpretability into the fair representation framework.…”

Section: Proposed Taxonomy Of Fairxaimentioning

confidence: 99%

See 2 more Smart Citations

FairXAI - A Taxonomy and Framework for Fairness and Explainability Synergy in Machine Learning

Ramachandranpillai,

Baeza-Yates,

Heintz

2023

Preprint

View full text Add to dashboard Cite

<p>Explainable Artificial Intelligence (XAI) and Fair Learning have made significant strides in various application domains, including criminal recidivism predictions, healthcare settings, toxic comment detection, automatic speech detection, recommendation systems, and image segmentation. However, these two fields have largely evolved independently. Recent studies have demonstrated that incorporating explanations into decision-making processes enhances the transparency and trustworthiness of AI systems. In light of this, our objective is to conduct a systematic review of FairXAI, which explores the interplay between fairness and explainability frameworks. To commence, we propose a taxonomy of FairXAI that utilizes XAI as a means to both mitigate and evaluate bias. This taxonomy will serve as a base for machine learning researchers operating in diverse domains. Additionally, we will undertake an extensive review of existing articles, taking into account factors such as the purpose of the interaction, target audience, and domain and context. Moreover, we outline an interaction framework for FairXAI considering various fairness perceptions and propose a FairXAI wheel that encompasses four core properties that must be verified and evaluated. This will serve as a practical tool for researchers and practitioners, ensuring the fairness and transparency of their AI systems. Furthermore, we will identify challenges and conflicts in the interactions between fairness and explainability, which could potentially pave the way for enhancing the responsibility of AI systems. As the inaugural review of its kind, we hope that this survey will inspire scholars to address these challenges by scrutinizing current research in their respective domains. </p>

show abstract

“…1) Intrinsic: Here, we restrict to include those intrinsic methods that explicitly considered fairness notions in their study [49]- [62].…”

Section: A Result-oriented Fairnessmentioning

confidence: 99%

Section: A Result-oriented Fairnessmentioning

confidence: 99%

See 1 more Smart Citation

FairXAI - A Taxonomy and Framework for Fairness and Explainability Synergy in Machine Learning

Ramachandranpillai,

Baeza-Yates,

Heintz

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…However, one problem with learning latent representations is their explainability. The projection into a latent space makes it difficult to investigate why the decision was made [7].…”

Section: Introductionmentioning

confidence: 99%

Towards Explainability of the Latent Space by Disentangled Representation Learning

Namatēvs,

Ņikuļins,

Slaidiņa

et al. 2023

ITMS

View full text Add to dashboard Cite

Deep neural networks are widely used in computer vision for image classification, segmentation and generation. They are also often criticised as “black boxes” because their decision-making process is often not interpretable by humans. However, learning explainable representations that explicitly disentangle the underlying mechanisms that structure observational data is still a challenge. To further explore the latent space and achieve generic processing, we propose a pipeline for discovering the explainable directions in the latent space of generative models. Since the latent space contains semantically meaningful directions and can be explained, we propose a pipeline to fully resolve the representation of the latent space. It consists of a Dirichlet encoder, conditional deterministic diffusion, a group-swap and a latent traversal module. We believe that this study provides an insight into the advancement of research explaining the disentanglement of neural networks in the community.

show abstract

Fair Interpretable Representation Learning with Correction Vectors

Cited by 2 publications

References 25 publications

FairXAI - A Taxonomy and Framework for Fairness and Explainability Synergy in Machine Learning

FairXAI - A Taxonomy and Framework for Fairness and Explainability Synergy in Machine Learning

Towards Explainability of the Latent Space by Disentangled Representation Learning

Contact Info

Product

Resources

About