Generative model controls text attributes for realistic sentences.
problem Challenges in generating natural language sentences with desired attributes.
method Combines variational auto-encoders and holistic attribute discriminators for semantic structure imposition.
result Effective generation of realistic sentences with desired attributes.
Paper develops methods for fair insurance pricing without direct access to sensitive attributes.
problem Fairness in insurance pricing with restricted access to sensitive attributes.
method Develops statistical methods for estimating discrimination-free premiums using privatized sensitive attributes.
result The proposed methods enable fair insurance pricing while respecting privacy and regulatory constraints.
Enhances dialogue model with persona attributes using adversarial learning.
problem Improving dialogue models to better capture speaker identity and topic.
method Adversarial learning framework with a dual discriminator system.
result phredGAN outperforms persona Seq2Seq model in various datasets.
FairUDT uses uplift decision trees to detect and mitigate discrimination in training data.
problem Bias in machine learning classifiers due to historical discrimination or underrepresentation of minority groups.
method Integrates uplift modeling with decision trees and introduces a modified leaf relabeling approach for fairness.
result Achieves an acceptable accuracy-discrimination tradeoff while maintaining interpretability.
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.
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.
Paper proposes a method to identify and treat latent discriminating features in machine learning models.
problem Fairness issues in machine learning models trained on historical data containing sensitive attributes.
method A novel algorithm that identifies and treats latent discriminating features, agnostic of the learning algorithm.
result Experimental results show near-ideal fairness measurement compared to other methods.
HC test measures word-frequency similarity for authorship attribution.
problem Identifying the author of a document based on word-frequency patterns.
method Adapting Higher Criticism (HC) to compare word-frequency tables.
result HC identifies characteristic words of the author, unaffected by topic structure.
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.
Paper presents mdfa to identify victims of discrimination in black box classifiers.
problem Identifying victims of discrimination in black box classifiers.
method Reduces discrimination measurement to matching distributions and sensitive attribute coincidence prediction.
result Identifies African-American individuals at high risk of violent recidivism.
The paper tackles fairness in algorithmic decision making using causal models.
problem Ensuring algorithmic decision making systems do not discriminate based on protected attributes.
method Introduces two definitions of group fairness (FACE and FACT) grounded in causal models and uses Rubin-Neyman potential outcomes framework for robust estimation.
result Demonstrates the effectiveness of FACE and FACT in detecting discrimination in real-world data sets.
Secure methods learn fair models without revealing sensitive attributes.
problem Training fair machine learning models without exposing sensitive data.
method Secure multi-party computation to encrypt sensitive attributes.
result Outcome-based fair models can be learned, checked, or verified without revealing sensitive attributes.
Two-stage algorithm removes bias in machine learning decisions.
problem Bias in machine learning decisions can unfairly discriminate specific groups.
method Inspired by two-stage least squares, a two-stage algorithm that removes bias in training data.
result The algorithm avoids disparate impact when making decisions.
Machine learning algorithms can unintentionally discriminate; tools detect and fix this.
problem Unintentional discrimination in machine learning algorithms.
method Statistical tools to detect and eliminate biases.
result Tools can identify and mitigate algorithmic discrimination.
Develops Triangle GAN for semi-supervised cross-domain learning.
problem Semi-supervised cross-domain joint distribution matching with limited labeled data.
method Triangle GAN architecture with two generators and two discriminators trained adversarially.
result Generators learn conditional distributions between domains, discriminators define ternary function.
SEAL improves AL on attributed graphs by combining deep learning and adversarial strategies.
problem Efficient AL on attributed graphs with label sparsity issues.
method SEAL framework using adversarial components for graph embedding and semi-supervised discriminator.
result Superior performance improvements over state-of-the-art baselines.
DMGI embeds multiplex networks with node attributes without supervision.
problem Existing methods fail to handle node attributes and multiple relation types in multiplex networks.
method Inspired by DGI, DMGI maximizes mutual information between local and global graph representations, integrating node embeddings from multiple graphs.
result DMGI outperforms state-of-the-art methods on various downstream tasks.
Paper protects privacy and fairness in deep learning models.
problem Ensuring fairness in deep learning models while protecting sensitive data.
method Uses differential privacy and Lagrangian duality to design fair predictors.
result Demonstrates improved model performance on prediction tasks.
New technique reduces bias in DNN models without sensitive attribute annotations.
problem Existing bias mitigation methods require instance-level annotations and do not guarantee removal of all sensitive information.
method Representation Neutralization for Fairness (RNF) debiases only the classification head of DNN models using neutralized representations.
result RNF effectively reduces discrimination of DNN models with minimal performance degradation.
The paper tackles multi-level fairness in algorithmic systems, addressing bias at both individual and structural levels.
problem Algorithmic systems can unfairly impact marginalized groups, especially when considering only individual-level bias.
method Formalizes multi-level fairness using causal inference tools, addressing effects of sensitive attributes at multiple levels.
result Illustrates the importance of accounting for macro-level sensitive attributes in fairness assessments.
In principle, zero-shot learning makes it possible to train a recognition model simply by specifying the category's attributes. For example, with classifiers for generic attributes like \emph{striped} and \emph{four-legged}, one can construct a classifier for the zebra category by enumerating which properties it posses…
CST detects discrimination by comparing protected and non-protected individuals with a counterfactual.
problem Detecting discrimination in classifiers using legal fairness conditions.
method Operationalizes fairness given the difference using counterfactual reasoning.
result CST uncovers more discrimination cases than traditional situation testing.
The study tests and optimizes fairness in credit scoring models.
problem Discrimination in credit scoring models based on protected attributes.
method Formal testing and variable identification to optimize fairness and performance.
result Guidance on monitoring and improving algorithmic fairness in credit scoring.
Simpler method for separating and manipulating latent attributes in autoencoders.
problem Separating and manipulating latent attributes in autoencoders.
method Matrix subspace projection
result Our method allows for changing selected attributes while preserving other information.
GRAD simplifies making neural networks fair.
problem No methods for making neural networks fair.
method Gradient Reversal Against Discrimination (GRAD)
result Improved individual and group fairness.
The paper explores intersectional fairness in machine learning, proving bounds on it.
problem Intersectional fairness in machine learning, especially when multiple protected attributes are involved.
method Statistical analysis and bounds on intersectional fairness, leveraging marginal fairness.
result Theoretical bounds on intersectional fairness can be computed from marginal fairness and other statistical quantities.
fairadapt uses causal inference to mitigate algorithmic bias in data pre-processing.
problem Mitigating algorithmic bias in machine learning predictions.
method Causal graphical model and observed data to address counterfactual questions.
result The method can help eliminate discrimination and justify fair decisions.
New method for fair influence maximization in social networks.
problem Maximizing influence while ensuring fairness across sensitive attributes.
method Co-training an auto-encoder and discriminator to create fair graph embeddings.
result Our method reduces disparity while maintaining competitive influence maximization performance.
Develops algorithm to make fair decisions from biased data.
problem Ethical concerns in machine learning fairness.
method Fair Learning through Data Preprocessing (FLAP) algorithm.
result Counterfactual fairness equivalent to conditional independence.
Obtaining compact and discriminative features is one of the major challenges in many of the real-world image classification tasks such as face verification and object recognition. One possible approach is to represent input image on the basis of high-level features that carry semantic meaning which humans can understan…
Fairness in Naive Bayes classifiers by identifying and eliminating discrimination patterns.
problem Ensuring fairness in machine learning models that use partial observations.
method Discover and eliminate discrimination patterns in naive Bayes classifiers through iterative learning.
result An algorithm that learns fair naive Bayes classifiers by removing discrimination patterns.
Semi-supervised GAN learns from both labeled and unlabeled data.
problem Conditional generation with limited labeled data.
method Stacked discriminators for marginal and conditional learning.
result Significantly better performance compared to existing 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.
Paper explores combining auto-encoder representations to fool adversarial discriminators.
problem Combining auto-encoder representations to fool adversarial discriminators.
method Mixing function to produce interpolations of hidden states or masked combinations of latent representations.
result Shows that mixing function can produce interpolations consistent with a conditioned class label.
We introduce the "Energy-based Generative Adversarial Network" model (EBGAN) which views the discriminator as an energy function that attributes low energies to the regions near the data manifold and higher energies to other regions. Similar to the probabilistic GANs, a generator is seen as being trained to produce con…
Paper proposes a new FRL algorithm for continuous sensitive attributes using EIPM.
problem Existing FRL algorithms cannot handle continuous sensitive attributes.
method Introduces EIPM to assess fairness in representation space for continuous attributes and proposes FREM algorithm.
result FREM outperforms other methods in fairness evaluation for continuous sensitive attributes.
This research compares two encoding methods for categorical attributes in machine learning, affecting model fairness.
problem The impact of encoding protected categorical attributes on fairness in machine learning models.
method Comparison of one-hot encoding and target encoding methods.
result Target encoding can lead to more unfair models compared to one-hot encoding due to induced bias.
Proposes a new method for fairness in machine learning with multiple protected attributes.
problem Ensuring fairness in machine learning models with continuous and multiple protected attributes.
method Distance covariance regularisation framework to mitigate association between model predictions and protected attributes.
result Demonstrates effectiveness in mitigating fairness gerrymandering in regression tasks.
A Longitudinal Attribute-Conditioned Neural Network (LANTERN) framework for modeling health-state transition probabilities in irregular longitudinal data.
problem Estimating long-term care transition probabilities in irregular longitudinal health data.
method A neural network that learns from individual health history, incorporates time elapsed, and conditions on demographic and socioeconomic attributes.
result Improves severe disability discrimination and maintains strong calibration.
A new method for name disambiguation in academic networks using multi-view attention and recurrent neural networks.
problem Disambiguating authors with the same name in large-scale academic networks.
method Multi-view Attention-based Pairwise Recurrent Neural Network (MA-PairRNN) that divides papers into blocks based on author attributes and merges blocks of the same author.
result MA-PairRNN significantly improves name disambiguation performance on real-world datasets.
The paper tackles fair ranking in ranked data by addressing causal discrimination.
problem Fairness in predictive models for ranked data.
method Mapping rank positions to continuous scores, building causal graphs, and using path-specific effects.
result Effective algorithms for discovering and removing discrimination from ranked datasets.
Optimal transport framework for zero-shot learning.
problem Generalized zero-shot learning of unseen classes.
method Conditional generative model and optimal transport between generated and real features.
result Optimal transport-based method outperforms state-of-the-art methods.
The insurance industry uses predictions based on customer characteristics, but this can lead to discrimination. We propose using Wasserstein barycenters to mitigate biases.
problem Discrimination in insurance predictions based on sensitive features like gender or race.
method Propose using Wasserstein barycenters instead of simple scaling to mitigate biases in insurance predictions.
result Demonstrates the effectiveness of Wasserstein barycenters in mitigating biases in insurance predictions.
PathBoost boosts graph-level predictions using path-based features.
problem Graph-level classification and regression challenges.
method Gradient tree boosting method for graph-level prediction.
result PathBoost outperforms graph neural networks and graph kernel approaches in many cases.
New research shows input-gradients can be manipulated without changing model's core function, challenging their use for model interpretation.
problem Current methods for model interpretability using input-gradients are flawed due to their arbitrary manipulability.
method Investigated by reinterpreting logits as unnormalized log-densities, proposing novel approximations for score-matching.
result Improving alignment between implicit density model and data distribution enhances gradient structure and explanatory power.
Medical imaging models may encode demographic attributes without violating fairness, depending on the approach.
problem Discrimination in medical imaging models due to encoding demographic attributes.
method Examined marginal and class-conditional representation invariance, traditional fairness notions, and counterfactual fairness.
result Demographically invariant models may not necessarily be fair, and encoding demographic attributes can be advantageous.
A new method improves node classification in graphs with limited labels.
problem Semi-supervised multi-label node classification in attributed graphs.
method Collaborative Graph Walk (Multi-Label-Graph-Walk) using reinforcement learning.
result Significantly better multi-label classification performance compared to state-of-the-art methods.
New method detects and mitigates historical bias in data.
problem Detecting and explaining historical bias in data.
method Developed a sample bias criterion and algorithms to measure and counter sample bias.
result Derived bias score provides sample-level attribution and explanation of historical bias.