Paper optimizes data preprocessing to prevent discrimination.
problem Reducing discrimination in algorithmic decision-making.
method Convex optimization for data transformation with three goals: controlling discrimination, limiting distortion, and preserving utility.
result All three criteria can be simultaneously achieved, revealing interesting patterns of bias.
FairGAN generates fair data to prevent discrimination in GANs.
problem Preventing discrimination in generated data.
method FairGAN uses GANs to learn fair data generation.
result FairGAN generates fair data that also preserves data utility.
Machine learning algorithms can unintentionally discriminate, requiring new principles for fairness.
problem Unintentional discrimination in machine learning algorithms.
method Develop theoretical understanding and global optimization criteria for machine learning fairness.
result Establish fundamental principles for preventing algorithmic discrimination.
This paper discusses fairness in machine learning and its legal implications.
problem Discrimination in machine learning algorithms that unfairly treat certain groups.
method Explains moral philosophy, legislation, and strategies to detect and prevent discrimination.
result Discusses the need for fairness in machine learning and legal measures to enforce it.
The paper examines GANs' forgetting and mode collapse, showing how they relate and impact training.
problem Catastrophic forgetting and mode collapse in GANs during continual learning.
method Investigates the continual learning nature of GANs, analyzing discriminator's output landscapes and convergence.
result Catastrophic forgetting and mode collapse are interrelated and prevent GANs from converging.
Confidential Guardian prevents model abstention from being used to discriminate.
problem Dishonest institutions can exploit machine learning model abstention to unfairly deny services.
method Confidential Guardian uses zero-knowledge proofs to verify model confidence and detect suppression.
result Confidential Guardian effectively prevents the misuse of cautious predictions.
Discriminators can be good feature extractors despite their task focus.
problem Discriminators' features are often considered useless for downstream tasks.
method Theoretical analysis and feature space examination to understand discriminator's role.
result Discriminator features are robust and can prevent mode collapse, making them useful for transfer learning.
Self-supervised GAN prevents forgetting in sequential tasks.
problem Discriminator forgetting in GANs leads to training instability.
method Add self-supervision to the discriminator to maintain useful representations.
result Self-supervised GAN outperforms regular GANs in learning better representations.
GANsan removes sensitive attributes from data to prevent discrimination.
problem Preventing discrimination in automated decision processes.
method Generative adversarial networks (GANs) to modify attributes without losing interpretability.
result Demonstrated effectiveness and trade-off between fairness and utility on real data.
New method improves GANs by training a mixed batch discriminator.
problem GANs struggle with mode collapse due to focusing on individual samples.
method Train a discriminator on mixed batches of true and fake samples.
result Significantly reduces mode collapse in GANs on various datasets.
New approach uses causal reasoning to address fairness issues.
problem Fairness criteria based on observational data are limited and unreliable.
method Shifts focus from observational criteria to causal reasoning.
result Formalizes why and when observational criteria fail.
New method detects and prevents unfairness in few-shot regression models.
problem Fairness issues in supervised few-shot meta-learning models.
method Causal Bayesian knowledge graph for dependency visualization, risk difference quantification, and fast-adapted bias-control approach.
result Efficiently detects and mitigates unfairness in model predictions.
DoPaNet uses multiple discriminators to prevent mode collapse in GANs.
problem Mode collapse in adversarial training.
method Employing multiple discriminators and a classifier to guide the generator.
result DoPaNet effectively covers the target distribution and outperforms competing methods.
The paper develops fair SVM algorithms that prevent bias in predictions.
problem Designing fair classifiers that prevent implicit biases.
method Develops iterative algorithms to compute fair linear and kernel SVM's, solving a sequence of relaxations using spectral decomposition.
result Effective in achieving high prediction accuracy while ensuring fairness.
Framework audits synthetic datasets for trustworthiness across various use cases.
problem Assessing the trustworthiness of synthetic datasets and models.
method Holistic auditing framework focusing on bias, fidelity, utility, robustness, and privacy.
result Introduces a trustworthiness index and model selection process for controllable trade-offs.
New method reduces indirect discrimination in insurance risk models.
problem Indirect discrimination in insurance risk models using machine learning.
method Mathematical concepts of linear algebra to reduce indirect discrimination.
result Demonstrated promising performance in a concrete case of risk selection in life insurance.
The paper introduces a method to eliminate latent discrimination in predictive models.
problem Controlling for latent discrimination in predictive models.
method Defining a new fairness criterion inspired by omitted variable bias, and a training strategy that includes sensitive features during training and excludes them during testing.
result A simple yet effective strategy to eliminate latent discrimination in predictive models.
Proposes fair mapping to prevent bias in model predictions without distorting data.
problem Reduces bias in model predictions without altering the data distribution.
method Uses Wasserstein GAN and AttGAN frameworks to transform data distributions while preserving privacy and interpretability.
result Preserves data interpretability and fairness in subsequent analysis tasks.
Study compares employers with and without anticipating strategic labor force responses.
problem Understanding and optimizing strategic interactions in labor markets.
method Formulation of causal strategic classification, theory, and experiments.
result Performatively optimal hiring policies improve employer and labor outcomes, but can also harm labor force utility.
Improves GAN performance without changing network architecture.
problem Discriminator fails to guide generator effectively.
method Cascading Rejection (CR) module for discriminator.
result Significantly improves GAN performance in terms of FID.
Interventional domain adaptation improves feature transferability by removing spurious correlations.
problem Improper feature transferability due to spurious correlations in domain adaptation.
method Intervention strategy using unlabeled target data to generate counterfactual features and train discriminability invariance.
result Consistent performance improvements over state-of-the-art approaches in various domain adaptation tasks.
Unbalanced GANs stabilize GAN training by pre-training the generator with VAE.
problem Stable training of GANs to avoid mode collapses and improve image quality.
method Pre-train GAN generator with VAE, balance generator and discriminator training, prevent discriminator's early convergence.
result Unbalanced GANs reduce mode collapses and outperform ordinary GANs in stability, convergence, and image quality.
EVCL combines VCL and EWC to prevent forgetting new tasks.
problem Preventing catastrophic forgetting in continual learning.
method Hybrid model integrating VCL and EWC.
result Consistently outperforms baselines in learning new tasks.
TripletGAN uses triplet loss to improve generative models, preventing mode collapse.
problem Mode collapse in generative models.
method Substituting discriminator's classification loss with triplet loss.
result TripletGAN helps prevent mode collapse and converges to the given distribution.
The paper tackles fairness in supervised learning using information theory.
problem Discrimination in decision rules derived from biased historical data.
method Information theoretic framework for designing fair predictors, using equalized odds criterion.
result Designing predictors that are independent of a sensitive attribute while generalizing well.
Surveying fairness formalizations in machine learning for prediction.
problem Preventing algorithmic discrimination in critical decisions.
method Survey and critique of existing fairness formalizations from machine learning and social sciences.
result Limitations of existing fairness formalizations and suggestions for new ones.
Local discovery method uncovers direct unfairness in complex systems.
problem Identifying causal pathways of unfairness in complex domains.
method Local discovery for direct discrimination (LD3) method.
result LD3 returns a valid adjustment set (VAS) for assessing unfairness.
This paper develops a machine learning model to assess credit risk in UAE commercial banks.
problem Lack of precision in conventional credit rating tools for accurate credit risk prediction.
method Constructs a credit risk assessment model using Linear Discriminant Analysis.
result Demonstrates improved accuracy in predicting good and bad creditors compared to conventional methods.
SR-GANs combat mode collapse in GANs by monitoring and compensating spectral distributions.
problem Mode collapse in GANs.
method Spectral regularization (SR-GANs) to combat spectral collapse.
result SR-GANs prevent mode collapse and outperform SN-GANs in experiments.
A new GAN framework GAN-QP avoids gradient vanishing and 1-Lipschitz constraint.
problem Gradient vanishing and 1-Lipschitz constraint in GANs.
method Construct a new GAN framework GAN-QP by eliminating the first step of divergence conversion.
result GAN-QP outperforms WGAN in theory and practice.
Study uses EEG features HFD and SampEn to detect depression with high accuracy.
problem Diagnosing depression reliably and accurately.
method Applied Higuchi Fractal Dimension and Sample Entropy on EEG signals using seven machine learning algorithms.
result Good classification possible even with small EEG data, achieving high accuracy.
AFTER technique improves NLP models by preventing overfitting to task-specific domains.
problem Standard fine-tuning degrades pretraining domain representations.
method Complements task-specific loss with adversarial objective.
result AFTER leads to improved performance on various NLP tasks.
Improved GAN training stability through clipping and reweighting.
problem Inconsistent GAN training leading to inferior performance.
method Proposes a variational GAN framework with probability ratio clipping and sample reweighting.
result Significantly improved performance across various GAN tasks.
Adversarial learning prevents sensitive information from representations.
problem Preventing discrimination and removing private information from representations.
method Learning flexible representations by minimizing an adversarial critic's performance.
result Statistically significant improvement in fairness across most cases.
This thesis tackles data imperfections in ML, proposing methods to prevent discrimination and spurious feature learning.
problem Data imperfections in ML training data, leading to deployment failures.
method Fair representation learning, spurious feature detection, and data augmentation for reinforcement learning.
result Methods to make ML models more robust to data imperfections.
Wide neural networks with narrow bottlenecks behave like deep Gaussian processes.
problem Understanding the behavior of neural networks with narrow layers in the wide limit.
method Analyzing the wide limit of BNNs with narrow bottlenecks, showing they behave like a composition of GPs.
result Wide neural networks with narrow bottlenecks form a composition of GPs, termed a bottleneck NNGP.
Paper proposes fair decision trees to avoid unfair treatment.
problem Discriminative decision-making in automated systems.
method Mixed-integer optimization framework for fair decision trees.
result Improves fairness and accuracy in decision-making.
Graph transformers outperform graph convolutions by preserving community information.
problem Understanding why graph transformers perform well in node-level prediction tasks.
method Analyzing the Gaussian process limits of graph transformers with infinite width and infinite heads.
result Graph transformers maintain discriminative node representations even in deep layers, preventing oversmoothing.
Improves neural networks' ability to learn new tasks without forgetting earlier ones.
problem Preventing catastrophic forgetting in neural networks.
method Introducing a second discriminator in the GAN to generate important features for task retention.
result Significant reduction in catastrophic forgetting compared to standard methods.
New method prevents forgetting in continual learning tasks.
problem Catastrophic forgetting in continual learning.
method Generative regularization integrated into Bayesian inference framework.
result Empirically outperforms state-of-the-art methods on various datasets.
Proposes a fair classification model using robust optimization.
problem Preventing discrimination in classification models.
method Distributionally robust logistic regression with Wasserstein ball and convex unfairness measure.
result Improves fairness with minimal loss in predictive accuracy.
This paper integrates auto-encoders and GANs using variational inference.
problem Preventing mode collapse in generative models.
method Develops a principle to combine variational auto-encoders and GANs, using synthetic likelihoods and implicit posterior distributions.
result Unified objective for optimizing the fusion of variational auto-encoders and GANs.
Proposes a self-adversarial variational autoencoder for anomaly detection.
problem Anomaly detection in deep generative models.
method Self-adversarial Variational Autoencoder with Gaussian anomaly prior.
result Significant improvements in anomaly detection performance compared to SOTA baselines.
New method detects anomalies using GAN with minimum likelihood regularization.
problem Detecting abnormal events in various domains.
method Generative Adversarial Networks with minimum likelihood regularization.
result Significant improvement over other methods on Cifar10 and UCI datasets.
This study predicts crime trends in Denver using machine learning.
problem Predicting crime patterns to aid law enforcement and resource allocation.
method Statistical analysis, data visualization, and various classification algorithms.
result Ensemble Model 4 achieved the highest accuracy in predicting crime.
Proposes RLAR for efficient labeled data classification with robust margin and manifold structure.
problem Clear margin representation and data manifold structure difficulty in linear discriminant methods.
method Introduces retargeted regression for adaptive margin learning and locality-aware strategy for compact data manifold.
result RLAR outperforms state-of-the-art approaches in UCI and benchmark data sets.
Proposes NC-VAE to prevent posterior collapse in VAEs.
problem Posterior collapse in variational autoencoders (VAEs).
method Noise contrastive estimation applied to VAEs.
result Proves NC-VAE cannot reach posterior collapse and provides lower bounds.
Proposes adversarial normalization for multi-domain image segmentation.
problem Current image normalization is per-dataset, limiting multi-domain segmentation.
method Adversarial training to learn common normalizing functions across multiple datasets.
result Optimal normalizer improves segmentation accuracy and realism.