The study explores fairness in classifier post-processing methods.
problem Achieving fairness in binary decision-making classifiers with imperfect information.
method Examines fairness properties of post-processing calibrated scores and deferring decisions.
result Deferring decisions can help achieve fairness in PPV, NPV, FPR, and FNR across protected groups.
Unified approach adjusts classifiers to meet system-level constraints.
problem Multi-class classification under system-level constraints.
method Post-processing approach using linearly constrained stochastic program and entropic regularization.
result Finite-sample guarantees for risk and constraint satisfaction.
New method wraps black-box classifiers to reduce bias.
problem Reduction of bias in black-box predictions.
method Post-processing with α-trees and boosting algorithms.
result Demonstrated effectiveness in reducing bias across multiple fairness metrics.
Accurate calibration of probabilistic predictive models learned is critical for many practical prediction and decision-making tasks. There are two main categories of methods for building calibrated classifiers. One approach is to develop methods for learning probabilistic models that are well-calibrated, ab initio. The…
Paper characterizes fairness vs. accuracy tradeoff in classification.
problem Mitigating bias in machine learning models.
method Characterizes the tradeoff between fairness and accuracy, provides a post-processing algorithm.
result Post-processing algorithm yields optimal fair classifier when score is Bayes optimal.
New method improves fairness in biased predictions.
problem Improving fairness in biased classifier predictions.
method Individual bias detector prioritizes data samples for a bias mitigation algorithm.
result Superior performance in individual and group fairness on real-world datasets.
New classifiers ensure fairness by adjusting a base classifier's operating characteristics.
problem Ensuring fairness in binary classification with multiple group constraints.
method Intervening directly on a base classifier's operating characteristics using group-wise ROC convex hulls and post-processing.
result Methods satisfy multiple fairness constraints (DP, EO, PP) with minimal interventions and near-oracle accuracy.
This work debiases deep chest X-ray classifiers using intra- and post-processing methods.
problem Bias in deep neural networks for chest X-ray classification.
method Intra-processing techniques (fine-tuning and pruning) and post-processing methods.
result Successfully mitigates biases in fully connected and convolutional neural networks, offering stable performance.
The paper addresses fairness issues in screening classifiers, proposing within-group monotonicity to avoid unfair treatment of qualified candidates.
problem Within-group unfairness in screening classifiers using calibrated models.
method Introducing within-group monotonicity as a property to avoid unfair treatment and developing an efficient post-processing algorithm based on dynamic programming.
result Within-group monotonicity can be achieved efficiently and often at a small cost, improving fairness without significantly compromising prediction accuracy.
This paper tackles tweet classification by identifying purpose and position.
problem Difficulties in determining user intention and attitude in short, informal tweets.
method Transformed tweet classification into a multi-label problem and applied a multi-label classification method with post-processing.
result The method effectively classifies tweet purpose and position, outperforming individual classification methods.
Develops methods for fair classification under linear disparity constraints.
problem Disparate impacts of machine learning algorithms on protected groups.
method Bayes-optimal fair classification methods via pre-, in-, and post-processing.
result Explicit forms of Bayes-optimal fair classifiers under linear disparity measures.
DEDPUL improves PU learning by estimating proportions and classifying unlabeled data.
problem Analog to supervised binary classification with only positive samples clean and unlabeled mixtures of positive and negative.
method Applies a post-processing procedure to any classifier trained to distinguish positive and unlabeled data, estimating proportions alongside classification.
result Outperforms state-of-the-art in both proportion estimation and PU classification.
This work builds a fair classification algorithm that abstains from making predictions.
problem Building a fair classification algorithm that incorporates human decision-making and avoids disparities.
method Formalizes the problem of risk minimization under fairness and abstention constraints, derives the optimal classifier, and proposes a post-processing algorithm using unlabeled data.
result The proposed algorithm achieves fairness and abstention guarantees independently of the initial classifier, provided sufficient unlabeled data is available.
Study evaluates post-processing methods for improving solar power forecasts.
problem Improving accuracy of probabilistic solar energy forecasts through model chain approaches.
method Systematically evaluates different post-processing strategies for ensemble weather forecasts and direct solar power forecasting.
result Post-processing significantly improves solar power generation forecasts, especially when applied to power predictions.
Improved visibility forecasts using statistical post-processing.
problem Accurate and reliable predictions of visibility are crucial in aviation and transportation.
method Calibrated ensemble forecasts using locally, semi-locally, and regionally trained POLR and MLP classifiers.
result Post-processing improves forecast skill and POLR models outperform MLPs.
Post-processing corrects bias in ML systems without retraining.
problem Correcting bias in ML systems that are already in use.
method Proposes general post-processing algorithms for individual fairness based on graph Laplacian regularization.
result Empirically, post-processing algorithms correct individual biases in large-scale NLP models while preserving accuracy.
MimickNet approximates clinical ultrasound post-processing without proprietary data.
problem Matching proprietary clinical-grade ultrasound post-processing techniques.
method Deep learning framework MimickNet that transforms raw DAS beams into post-processed images.
result MimickNet achieves high SSIM scores (0.930-0.967) on test sets.
Paper studies fair classification of functional data.
problem Mitigating disparities in functional data classification.
method Unified framework for fairness-aware functional classification.
result Established theoretical guarantees on fairness and excess risk controls.
Algorithm ensures demographic parity in regression without sensitive attribute data.
problem Performing regression with demographic parity constraints.
method Post-processing algorithm using accurate estimates and sensitive attribute predictor.
result Generates predictions meeting demographic parity constraint.
Risk-controlled post-processing optimizes decision policies under risk constraints.
problem Optimizing decision policies with risk constraints for better outcomes.
method Developed a post-processing algorithm that selects a threshold based on fitted fallback policy and score, leveraging tools from algorithmic stability and stochastic processes.
result The post-processed policy achieves precise expected risk control under exchangeability and meets or nearly meets risk budgets while preserving more agreement with the baseline.
Post-process Bayesian inference speeds up posterior approximation.
problem Leveraging pre-existing model evaluations for quick posterior approximation.
method Variational Sparse Bayesian Quadrature (VSBQ) using sparse Gaussian process (GP) surrogate model.
result VSBQ builds high-quality posterior approximations from existing optimization traces.
New algorithm reduces bias in trained models, near-optimal performance proven.
problem Reduction of bias in trained machine learning models.
method Scalable post-processing algorithm for debiasing trained models, including deep neural networks (DNNs).
result Proven to be near-optimal by bounding its excess Bayes risk.
Deep neural networks improve ensemble weather forecasts.
problem Improving accuracy and efficiency of ensemble weather forecasts.
method Mixed model combining subset of trajectories with deep neural networks for post-processing.
result Achieved over 14% relative improvement in ensemble forecast skill.
The paper explores how mixing and diffusion mechanisms can enhance privacy in data processing.
problem Enhancing privacy guarantees of data mechanisms through post-processing.
method The study uses Markov operators and coupling arguments to analyze privacy amplification.
result The introduction of a new family of diffusion-based mechanisms that are closed under post-processing.
A graph neural network improves multivariate post-processing of ensemble forecasts.
problem Systematic biases in ensemble forecasts and loss of dependencies across forecast dimensions.
method A composite-Loss Graph Neural Network (dualGNN) trained with a composite loss function combining ES and VS.
result The dualGNN outperforms traditional methods in multivariate verification metrics and captures spatial relationships.
Unsupervised method improves word vectors by suppressing high variance features.
problem Improving semantic information in word vectors.
method Using conceptors to suppress high variance features in word vectors.
result Post-processed word vectors outperform existing alternatives in lexical evaluation tasks.
A framework for multiclass/multioutput classification metrics, revealing geometric insights and consistency.
problem Developing robust metrics for multiclass/multioutput classification problems.
method Proposes a framework for constructing and analyzing multiclass/multioutput classification metrics, revealing geometric insights and characterizing averaging methodologies.
result Plug-in estimator based on the characterization is consistent and easily implemented.
Proposes FACT, a diagnostic for understanding group fairness trade-offs.
problem Group fairness notions often conflict with each other, requiring a cost in model performance.
method Characterizes trade-offs via the fairness-confusion tensor and optimizes accuracy and fairness objectives.
result Demonstrates the use of FACT on synthetic and real datasets to understand accuracy-fairness trade-offs.
New post-processing methods improve word embedding performance.
problem Boosting the performance of word embeddings for similarity and analogy tasks.
method Optimizing a semi-Riemannian manifold with Centralised Kernel Alignment (CKA) to shrink the covariance matrix towards a scaled identity matrix.
result Improved performance on downstream tasks after smoothing the spectrum of word vectors.
Post-processing predictors reduces calibration errors for decision-making.
problem Predictors with low calibration error for machine learning may have high error for decision-making.
method Post-processing with ε distance to calibration adds noise to make predictions differentially private.
result Post-processing achieves O(√ε) ECE and CDL, asymptotically optimal.
Neural network-based post-processing improves ensemble forecast sharpness
problem Reducing the width of central prediction intervals in ensemble forecasts
method Extending loss function with a penalty term
result 8.2%-12.5% reduction in width of central prediction interval
Paper proposes a new method for probabilistic electricity price forecasting.
problem Accurate estimation of forecast uncertainties for optimal decision making.
method Implicit generative ensemble post-processing using an ensemble of point forecasting models.
result Method outperforms well-established model combination benchmarks.
Ensemble weather predictions require statistical post-processing of systematic errors to obtain reliable and accurate probabilistic forecasts. Traditionally, this is accomplished with distributional regression models in which the parameters of a predictive distribution are estimated from a training period. We propose a…
New method improves decision-making accuracy without complex calculations.
problem Improving decision-making accuracy in machine learning.
method Introducing a new measure called calibration decision loss (CDLK) for structured families of post-processing functions. result Proves upper and lower bounds for natural classes K of post-processing functions. Enhances fairness in multi-output models using optimal transport.
problem Improving fairness in multi-output models like multi-task/multi-class classification and representation learning.
method Post-processing method using optimal transport mappings to move model outputs towards empirical Wasserstein barycenter.
result Demonstrates effectiveness of the proposed approach on multi-task/multi-class classification and representation learning tasks.
Enhances fairness in predictions without sacrificing accuracy.
problem Balancing fairness and predictive performance in machine learning.
method Model ensemble-based post-processing framework.
result Framework effectively enhances fairness while maintaining predictive accuracy.
Develops a fair post-processing method for student success predictions.
problem Ensuring fairness in predictive student models for educational applications.
method Uses the MADD metric to improve model fairness while maintaining accuracy.
result Successfully improved fairness of predictive models for student success.
Meta-theorems validate fair regression algorithms under demographic parity constraints.
problem Regression under demographic parity constraints.
method Meta-theorems and post-processing methods.
result Fair minimax optimal regression can be achieved through post-processing.
Learning accurate probabilistic models from data is crucial in many practical tasks in data mining. In this paper we present a new non-parametric calibration method called \textit{ensemble of near isotonic regression} (ENIR). The method can be considered as an extension of BBQ, a recently proposed calibration method, a…
Enhanced visibility forecasts using CAMS data improve accuracy.
problem Improving the accuracy of visibility predictions in weather forecasts.
method Statistical post-processing with historical observations and CAMS forecasts.
result Post-processed forecasts with CAMS data are substantially superior to raw and climatological predictions.
The study compares statistical post-processing methods for solar radiation forecasts.
problem Improving accuracy and uncertainty quantification of solar radiation forecasts.
method Statistical post-processing techniques using relationships between meteorological variables and solar radiation.
result Quantile regression and generalized random forests generally perform best in probabilistic forecasts.
The paper tackles fair classification with multiple sensitive features.
problem Existing fair classification methods often consider a single sensitive feature, but in practice, individuals are defined by multiple sensitive features.
method Characterizes Bayes-optimal fair classifiers for multiple sensitive features under various fairness measures, proposing in-processing and post-processing algorithms.
result Bayes-optimal fair classifiers for multiple sensitive features are instance-dependent thresholding rules that rely on a weighted sum of group membership probabilities.
UPM clusters product titles for efficient unsupervised matching.
problem Matching product titles accurately in e-commerce.
method Clustering-based approach using title combinations.
result UPM outperforms state-of-the-art methods in efficiency and effectiveness.
ForestPrune optimizes tree ensemble pruning for compactness and speed.
problem Large tree ensembles in predictive models consume excessive memory and reduce interpretability.
method Developed a specialized optimization algorithm to efficiently prune tree ensembles by depth layers.
result ForestPrune produces compact, high-performing models that outperform existing post-processing methods.
In this article, we have proposed several approaches for post processing a large ensemble of prediction models or rules. The results from our simulations show that the post processing methods we have considered here are promising. We have used the techniques developed here for estimation of quantitative traits from mar…
Study on fair learning under differential privacy constraints.
problem Creating fair models without sensitive attribute data.
method Two algorithms: one using explicit group membership, the other not.
result Tradeoffs between fairness, accuracy, and privacy.
Improves probability estimates for small datasets in multi-class problems.
problem Inaccurate probability estimates in classification tasks, especially on small datasets.
method Introduced Data Generation and Grouping algorithm to improve calibration on small datasets, then applied to multi-class problems.
result Calibration error can be decreased using the proposed approach.
GAMA is a user-friendly AutoML system for machine learning pipeline optimization.
problem Empowering users to control and optimize machine learning pipelines.
method Modular AutoML system with three search algorithms and two post-processing steps.
result GAMA allows users to track and control the search process for optimal machine learning pipelines.