This paper evaluates debiasing methods on word embeddings to reduce religious bias.
problem Social biases persist in word embeddings, potentially amplifying them in AI applications.
method Investigates and evaluates three multiclass debiasing techniques on three word embeddings.
result ConceptorDebiasing is the most effective method, reducing religious bias by 82-96%.
A new algorithm removes unexpected correlations in biased data for better clustering.
problem Clustering with selection bias in data.
method Decorrelation regularized K-Means (DCKM) algorithm.
result DCKM achieves significant performance gains on real-world datasets.
The influence of human judgement is ubiquitous in datasets used across the analytics industry, yet humans are known to be sub-optimal decision makers prone to various biases. Analysing biased datasets then leads to biased outcomes of the analysis. Bias by protected characteristics (e.g. race) is of particular interest …
GRASP removes spurious correlations in fine-tuned models, improving task performance and reducing bias.
problem Fine-tuned models can latch onto spurious correlations, leading to bias and reduced generalization.
method GRASP identifies and removes spurious correlations from model weights without removing latent factors.
result GRASP significantly reduces bias and improves task performance in various fine-tuning tasks.
Study removes bias from chest X-ray embeddings using orthogonalization.
problem Reduces bias in chest X-ray embeddings due to protected features.
method Orthogonalization technique to remove protected feature effects.
result Orthogonalization removes bias and makes predictions of protected attributes infeasible.
Reduces gender bias in patient notes while maintaining medical classification accuracy.
problem Bias in natural language processing of patient notes.
method Identifying and removing gendered language using BERT-based classifiers, then augmenting data to maintain performance.
result Minimal degradation in health condition classification tasks with data augmentation.
Semiparametric method removes bias in functional bilevel gradient estimation.
problem First-order bias in plug-in hypergradient when lower-level problem is nonparametric.
method Semiparametric debiasing theory based on efficient influence function leads to cross-fitted orthogonal hypergradient estimator.
result Asymptotic normality and uniform control over outer parameter established for the estimator.
Study finds gender bias in human evaluators and shows how machine learning can mitigate it.
problem Gender bias in human decision-making on micro-lending platforms.
method Structural econometric model and machine learning algorithms trained on real-world data.
result Machine learning algorithms can mitigate both preference-based and belief-based biases.
New method removes interference bias in causal models.
problem Interference bias impedes causal effect identification in real-world settings.
method Novel definition of causal models with local interference, semi-parametric assumptions.
result True Average Causal Effect can be identified in certain semi-parametric models with local interference.
Many modern Artificial Intelligence (AI) systems make use of data embeddings, particularly in the domain of Natural Language Processing (NLP). These embeddings are learnt from data that has been gathered "from the wild" and have been found to contain unwanted biases. In this paper we make three contributions towards me…
Mitigates gender bias amplification in model predictions.
problem Gender bias amplification in model predictions.
method Posterior regularization to mitigate bias.
result Almost removes gender bias amplification in model predictions.
Predictive modeling is increasingly being employed to assist human decision-makers. One purported advantage of replacing human judgment with computer models in high stakes settings-- such as sentencing, hiring, policing, college admissions, and parole decisions-- is the perceived "neutrality" of computers. It is argued…
A human-in-the-loop ML framework for precision dosing reduces expert workload and removes bias.
problem High cost of data annotation and lack of appropriate data for ML models.
method Incorporates human experts into the model learning loop to improve interpretability and reduce bias.
result The approach learns interpretable rules from data and potentially lowers expert workload.
Active learning introduces bias; this paper fixes it.
problem Bias in active learning due to non-representative training data.
method Formalized bias, identified situations where it's harmful/helpful, introduced corrective weights.
result Corrective weights can improve active learning, especially with overparameterized models.
This paper proposes a novel Gaussian process approach to fault removal in time-series data. Fault removal does not delete the faulty signal data but, instead, massages the fault from the data. We assume that only one fault occurs at any one time and model the signal by two separate non-parametric Gaussian process model…
Paper tackles treatment leakage in text-based causal inference, proposing methods to mitigate bias.
problem Treatment leakage in text-as-confounder applications introduces bias in causal estimates.
method Formal definitions, four text distillation methods (passage removal, classification, salient feature removal, nullspace projection).
result Moderate distillation optimally balances bias reduction against confounder retention.
The paper detects and identifies bias in data using a counterfactual approach.
problem Detecting and identifying bias in data, especially in medical image classification.
method A global explanation framework using the counterfactual approach to identify bias causing artifacts.
result Black frames significantly influence Convolutional Neural Network's prediction, changing benign to malignant.
Algorithmic decision making process now affects many aspects of our lives. Standard tools for machine learning, such as classification and regression, are subject to the bias in data, and thus direct application of such off-the-shelf tools could lead to a specific group being unfairly discriminated. Removing sensitive …
Machine learning confound removal biases results, leading to misleading predictions.
problem Common confound removal methods in machine learning lead to misleading predictions.
method Featurewise removal of confound variance by linear regression before applying ML.
result This common deconfounding approach can leak information, amplifying null or moderate effects.
Adversarial domain adaptation reduces sample bias in high energy physics classifier.
problem Sample bias in high energy physics classifier training.
method Adversarial domain adaptation using neural networks with gradient reversal layer.
result Successful bias removal on simulated events at the LHC.
New models avoid lookahead bias by training on past data only.
problem Lookahead bias in language models.
method Chronologically consistent training on data before a knowledge-cutoff date.
result Elimination of lookahead bias in predictions.
This research debiases machine unlearning by using counterfactual examples.
problem Machine unlearning processes can be biased, leading to inaccurate results.
method Intervention-based approach using counterfactual examples to mitigate biases.
result The method outperforms existing baselines on evaluation metrics.
Convolutional Neural Networks (CNNs) have become the state-of-the-art method to learn from image data. However, recent research shows that they may include a texture and colour bias in their representation, contrary to the intuition that they learn the shapes of the image content and to human biological learning. Thus,…
In real world systems, the predictions of deployed Machine Learned models affect the training data available to build subsequent models. This introduces a bias in the training data that needs to be addressed. Existing solutions to this problem attempt to resolve the problem by either casting this in the reinforcement l…
The power of machine learning systems not only promises great technical progress, but risks societal harm. As a recent example, researchers have shown that popular word embedding algorithms exhibit stereotypical biases, such as gender bias. The widespread use of these algorithms in machine learning systems, from automa…
A method removes treatment-covariate dependence for counterfactual prediction without adversarial training.
problem Counterfactual prediction under assignment bias.
method Information-theoretic approach learning a stochastic representation Z to minimize mutual information with outcomes.
result The method performs favorably in likelihood, counterfactual error, and policy evaluation compared to adversarial baselines.
New method reduces privacy impact on model accuracy for underrepresented groups.
problem Privacy mechanisms disproportionately affect underrepresented groups in machine learning models.
method Proposes DPSGD-F, a modified DPSGD that adjusts group contributions based on clipping bias.
result DPSGD-F removes disparate impact of differential privacy on model accuracy for protected groups.
Recent years have seen much research on fairness in machine learning. Here, mean difference (MD) or demographic parity is one of the most popular measures of fairness. However, MD quantifies not only discrimination but also explanatory bias which is the difference of outcomes justified by explanatory features. In this …
Improved preterm prediction using synthetic EHG signals.
problem Prediction bias towards term labor in preterm EHG data.
method Quantifying synthetic samples' effect, optimizing feature weights, and combining activation functions.
result Substantial improvement in prediction precision.
FFN addresses spectral bias in neural value approximation, improving reinforcement learning performance.
problem Spectral bias in neural value approximation, leading to slow convergence and poor performance.
method Proposes Fourier feature networks (FFN) to overcome spectral bias by using a composite neural tangent kernel.
result FFN achieves state-of-the-art performance on challenging continuous control domains with faster convergence and better stability.
Noise-corrected Langevin algorithm improves sampling from noisy data.
problem Sampling from noisy data with biased score function.
method Noise-corrected Langevin algorithm using noisy score function.
result Bias due to noisy data is removed, improving sampling accuracy.
Exposure bias has been regarded as a central problem for auto-regressive language models (LM). It claims that teacher forcing would cause the test-time generation to be incrementally distorted due to the training-generation discrepancy. Although a lot of algorithms have been proposed to avoid teacher forcing and theref…
New attention model removes softmax, improving sequence length bias.
problem Softmax attention's limitations and sequence length bias.
method Replaces softmax with normalization in self-attention.
result Normalization leads to more robust and bias-free attention.
New method removes pseudo-label bias for unsupervised domain adaptation.
problem Class imbalance and distribution shift between domains.
method Implicit class-conditioned domain alignment without explicit pseudo-label optimization.
result Effective in handling within-domain class imbalance and between-domain class distribution shift.
Improved sampling from complex distributions with reduced bias.
problem Reducing bias in high-dimensional sampling algorithms.
method Hierarchical entropy analysis to weaken assumptions and expand scope.
result Bias reduction in low-dimensional marginals scales with lower dimension, not full dimension.
Theoretical limits show experimental data can falsify but not validate causal estimates from observational studies.
problem Fundamental limits on validating causal estimates using experimental data in observational studies.
method Impossible inference framework, Gaussian Process based approach.
result Experimental data can falsify but not validate causal estimates from observational studies.
We study sampling as optimization in the space of measures. We focus on gradient flow-based optimization with the Langevin dynamics as a case study. We investigate the source of the bias of the unadjusted Langevin algorithm (ULA) in discrete time, and consider how to remove or reduce the bias. We point out the difficul…
Anonymization reduces economic signal extraction from financial texts.
problem Reducing meaningful economic signals from financial texts due to anonymization.
method Analyzed the impact of anonymization on textual understanding and economic signal extraction.
result Information loss due to anonymization is severe and pervasive, outweighing its benefits in certain financial applications.
Cross-validation is the de facto standard for predictive model evaluation and selection. In proper use, it provides an unbiased estimate of a model's predictive performance. However, data sets often undergo various forms of data-dependent preprocessing, such as mean-centering, rescaling, dimensionality reduction, and o…
Anonymizing company names in financial news improves trading performance, contrary to initial expectations.
problem Look-ahead and distraction biases in sentiment analysis of financial news.
method Investigated trading strategies based on original and anonymized headlines, comparing performance.
result Anonymized headlines outperform original in-sample, suggesting distraction effect is stronger.
Deep convolutional networks often append additive constant ("bias") terms to their convolution operations, enabling a richer repertoire of functional mappings. Biases are also used to facilitate training, by subtracting mean response over batches of training images (a component of "batch normalization"). Recent state-o…
QFIL improves offline RL by filtering data to reduce bias and variance.
problem Improving offline reinforcement learning policies with limited data.
method QFIL uses a filtered dataset to improve policies, trading off bias and variance through quantile selection.
result QFIL provides a safe policy improvement step with function approximation and effectively balances bias and variance.
A new method guides neural networks to focus on specific features of input data.
problem Training neural networks to consider specific features of input data.
method Focus-and-Expand ( ax) method: Gradual manipulation of input features.
result Achieves state-of-the-art results in bias removal and image classification tasks.
New tensor formulation reveals gradient flow's bias in linear neural networks.
problem Understanding implicit bias in linear neural network training.
method Tensor formulation of neural networks, including fully-connected, diagonal, and convolutional networks.
result Gradient flow on linear tensor networks converges to solutions of specific optimization problems.
Efficiently removes specific data subsets without retraining for GDPR compliance.
problem Efficiently removing specific data subsets to comply with GDPR regulations.
method Statistical framework for machine unlearning with minimax optimality for squared loss.
result Developed Unlearning Least Squares (ULS) achieving minimax optimality for estimating model parameters.
New framework assesses value of labeled vs unlabeled data in latent variable models.
problem Determining the optimal use of labeled and unlabeled data in latent variable models.
method Developed a bias-variance decomposition of the generalization error for method-of-moments latent variable estimation, and introduced a correction for misspecification.
result Labeled data is more valuable than unlabeled data when models are misspecified, but this value can be reduced with correction.
Proposes TSCI method to infer causal effects with weak or invalid instruments using machine learning.
problem Causal inference with weak or invalid instrumental variables.
method Two-stage curvature identification (TSCI) using machine learning.
result Asymptotically unbiased and Gaussian estimator for causal effects.
New algorithm makes machine learning fairer by removing bias from data.
problem Reduces bias in machine learning models through orthogonal data transformation.
method Orthogonal to Bias (OB) algorithm based on structural causal models.
result Promotes counterfactual fairness without sacrificing model accuracy.