Machine learning models can lead to group representation disparity, affecting long-term retention.
problem Representation disparity in ML models can lead to group retention issues over time.
method Analyzed user dynamics and fairness criteria in a sequential decision-making framework.
result Representation disparity can worsen over time without proper fairness criteria.
Paper addresses the disparity between sampled and mean representations in disentangled learning.
problem Disparity between sampled and mean representations in disentangled learning.
method Proposes a method to eliminate the disparity by proving and utilizing the relationship between total correlation of sampled and mean representations for multivariate normal distributions.
result Demonstrates that a factorized mean representation can have lower total correlation than the sampled representation.
The paper studies and mitigates accuracy disparity in regression models.
problem Accuracy disparity between different demographic subgroups in high-stakes domains.
method Error decomposition theorem and distribution alignment algorithm.
result The proposed algorithm effectively mitigates accuracy disparity while maintaining predictive power.
End-to-end framework learns precise disparity for activity recognition.
problem Precise portrayal of intraclass disparity in activity recognition.
method Knowledge-directed adversarial learning framework with two competitive encoding distributions.
result Robust and generalizable performance on HAR benchmark datasets.
Algorithm learns fair representations without sacrificing accuracy across groups.
problem Mitigating disparity among different demographic subgroups in classification.
method Balanced error rate and conditional alignment of representations.
result Improves utility-fairness trade-off on balanced datasets.
The paper analyzes how deep neural networks handle noisy labels and finds disparate impacts.
problem Disparate impacts of noisy labels on instances with different representation frequencies.
method Quantifying harms, analyzing solutions, and comparing their impacts on different frequency instances.
result Existing solutions lead to disparate treatments, benefiting higher-frequency instances more.
Machine learning models (e.g., speech recognizers) are usually trained to minimize average loss, which results in representation disparity---minority groups (e.g., non-native speakers) contribute less to the training objective and thus tend to suffer higher loss. Worse, as model accuracy affects user retention, a minor…
Study identifies and measures biases in legal case data.
problem Addressing representation biases and sentencing disparities in legal case data.
method Utilizes two regression models: a baseline and a fair judge model.
result Quantifies biases across demographic groups in criminal data from Cook County (Illinois).
Selective regression allows abstention to improve fairness criteria.
problem Selective regression can exacerbate disparities between subgroups.
method Proposes new fairness criteria and two approaches to mitigate performance disparity.
result Proposed fairness criteria ensures performance improvement for every subgroup with reduced coverage.
This work explains the structural origins of attention sinks in LLMs.
problem Initial tokens disproportionately monopolize attention scores in LLMs.
method Traced to self-attention's value aggregation process and FFN layer activations.
result Attention sinks form due to variance discrepancy and dimension disparity.
Graph embeddings from commute networks identify socioeconomic disparities in urban areas.
problem Urban delineation and socioeconomic group identification.
method Graph Neural Network (GNN) for modeling commute networks and deriving node embeddings.
result GNNs effectively capture socioeconomic disparities between urban communities.
This paper tackles fairness in PCA by balancing it with reconstruction error.
problem Fairness concerns in PCA due to different group representation errors.
method A multi-objective optimization approach to balance fairness and reconstruction error.
result Achieving fairness with minimal loss in reconstruction error.
Study shows unequal success of membership inference attacks across different groups.
problem Unequal success of membership inference attacks across different groups.
method Established conditions for preventing MIAs and derived connections to fairness and differential privacy.
result Estimating disparate vulnerability to MIAs can lead to overestimation; suitable attacks and statistical framework provided.
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.
Following related work in law and policy, two notions of disparity have come to shape the study of fairness in algorithmic decision-making. Algorithms exhibit treatment disparity if they formally treat members of protected subgroups differently; algorithms exhibit impact disparity when outcomes differ across subgroups,…
Study decomposes racial healthcare disparities via shifts in mediator distributions.
problem Racial disparities in healthcare expenditures and their underlying drivers.
method Framework decomposing disparities into mediator distribution shifts and residual components, using MEPS data.
result Substantial disparities persist even when mediators are equalized, suggesting unmeasured or structural factors.
Study shows explanation disparities in machine learning models are influenced by data and model properties.
problem Disparities in post-hoc machine learning explanation methods across race and gender.
method Simulations and experiments on a real-world dataset to assess challenges to explanation disparities.
result Increased covariate shift, concept shift, and omission of covariates increase explanation disparities, especially for neural network models.
Bayesian model identifies health disparities in disease progression.
problem Health disparities bias disease progression models.
method Interpretable Bayesian model accounting for three disparities.
result Model identifies and corrects for health disparities.
New approach for fair graph clustering using semidefinite relaxation.
problem Ensuring equitable representation in network analysis.
method Semidefinite relaxation approach for NP-hard optimization problem.
result Optimal accuracy-fairness trade-off achieved.
Study shows label errors impact model disparity metrics, proposing mitigation methods.
problem Impact of label errors on model disparity metrics.
method Empirical study, characterizing label error effects; proposing estimation and relabeling methods.
result Label errors significantly affect model disparity metrics, particularly for minority groups.
Proposes a method to quantify and decompose disparity in ML models, separating exempt and non-exempt components.
problem Quantifying disparity in ML models, especially when certain features are exempted due to their critical importance.
method Information-theoretic decomposition into exempt and non-exempt components, satisfying desirable properties.
result Proposes a measure of non-exempt disparity that satisfies all desirable properties, and shows impossibility results for observational measures.
BIND removes background noise from binary matrices, improving detection accuracy and fairness.
problem Real data often violates the i.i.d assumption for binary matrix entries, leading to inaccurate detection.
method BIND optimizes detection by estimating row- and column-wise mixture distributions and eliminating background noise.
result BIND effectively removes background noise and increases detection accuracy and fairness.
Paper explores fair classification with bounded disparity using finite datasets.
problem Ensuring fairness in binary classification with protected groups.
method Minimax optimal approach with fairness constraints and demographic disparity control.
result Proposes FairBayes-DDP+ method that achieves minimax lower bound on fairness-aware excess risk.
We provide the asymptotic distribution of the major indexes used in the statistical literature to quantify disparate treatment in machine learning. We aim at promoting the use of confidence intervals when testing the so-called group disparate impact. We illustrate on some examples the importance of using confidence int…
Automated data-driven decision making systems are increasingly being used to assist, or even replace humans in many settings. These systems function by learning from historical decisions, often taken by humans. In order to maximize the utility of these systems (or, classifiers), their training involves minimizing the e…
The paper examines how adversarial robustness affects accuracy disparity across different classes.
problem Understanding the impact of adversarial robustness on accuracy disparity across different classes.
method Linear classifiers under a Gaussian mixture model, decomposing the impact into inherent and imbalance effects.
result Adversarial robustness consistently degrades standard accuracy in balanced classes, but the class imbalance ratio plays a different role in accuracy disparity.
Paper tackles fairness in CCA by minimizing correlation disparity error.
problem Fairness issues in CCA.
method Framework to minimize correlation disparity error in CCA.
result Reduces correlation disparity error without sacrificing CCA accuracy.
New method evaluates multiple social disparities using machine learning.
problem Reduction of educational disparities across multiple dimensions.
method Triply-Robust Machine Learning Approach for Causal Decomposition Analysis.
result Simultaneous interventions across multiple domains reduce disparities.
Introduces MPR to measure and optimize representation across intersectional groups in retrieval.
problem Harmful stereotypes, cultural erasure, and social disparities in image search and retrieval.
method Develops MPR metric, practical estimation methods, theoretical guarantees, and optimization algorithms.
result Optimizing MPR yields more proportional representation across multiple intersectional groups, often with minimal retrieval accuracy compromise.
Study highlights fairness issues in travel behavior prediction models.
problem Ethical challenges in travel behavior analysis using machine learning.
method Operationalized computational fairness by equality of opportunity; compared DNN and DCM; introduced absolute correlation regularization.
result Both DNN and DCM predict disparities across social groups, with DNN outperforming DCM in prediction disparities.
Conformal prediction sets can lead to unfair outcomes.
problem Disparate impact in decision-making with conformal prediction sets.
method Experiments with human participants to demonstrate disparate impact and propose equalizing set sizes across groups.
result Providing prediction sets that satisfy Equalized Coverage increases disparate impact compared to marginal coverage.
Paper tackles fairness in algorithms by predicting protected class from auxiliary data.
problem Protected class membership is often unobserved in data, leading to unfair algorithmic decisions.
method Use auxiliary datasets to predict protected class from proxy variables and provide characterizations of possible disparities.
result Common disparity measures are generally unidentifiable with auxiliary data, highlighting the need for robust assessments.
When the performance of a machine learning model varies over groups defined by sensitive attributes (e.g., gender or ethnicity), the performance disparity can be expressed in terms of the probability distributions of the input and output variables over each group. In this paper, we exploit this fact to reduce the dispa…
We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and auxiliary, annotated datasets. We evaluate our approach on a variety of sequence cl…
DCEM algorithm reduces bias in machine learning models trained on selective labels.
problem Bias in machine learning models trained on selective labels.
method Disparate Censorship Expectation-Maximization (DCEM) algorithm.
result DCEM improves bias mitigation without sacrificing discriminative performance.
The paper introduces return parity for fairness in MDPs, addressing delayed and adverse effects.
problem Fairness in MDPs for dynamic domains with delayed and adverse effects.
method Proposes return parity, decomposes return disparity, and develops algorithms for state visitation distributional alignment.
result The proposed algorithms can successfully close the disparity gap while maintaining policy performance.
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.
A fair PCA method using JEVD ensures balanced data representation.
problem PCA's bias in data with demographic characteristics.
method Joint Eigenvalue Decomposition (JEVD) for fair PCA.
result JEVD optimally balances fairness and PCA's data structure.
The paper formalizes how concepts are encoded in text-guided generative models and provides a method to manipulate them.
problem Encoding and manipulating concepts in text-guided generative models.
method Formalizing concepts as subspaces of a representation space, developing algebraic manipulation methods.
result The ability to manipulate concepts in generative models through algebraic operations on the representation.
An increasing number of datasets contain multiple views, such as video, sound and automatic captions. A basic challenge in representation learning is how to leverage multiple views to learn better representations. This is further complicated by the existence of a latent alignment between views, such as between speech a…
Deep chest X-ray classifiers show bias in predicting diagnoses.
problem Bias in deep learning classifiers predicting diagnoses from chest X-rays.
method Trained convolutional neural networks on multiple public datasets to predict 14 diagnostic labels.
result True positive rates vary significantly among different protected attributes, indicating bias.
What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral. This legal determination hinges on a definition of a protected class (ethnicity, g…
Study breaks down graphs into structural and featural components for task-agnostic data valuation.
problem Lack of methods to assess the value of graphs in data marketplaces.
method Introduces blind message passing framework to evaluate graphs without specific task metrics.
result Demonstrates effectiveness in capturing structural disparities, relevance, and diversity of seller data for buyers.
New framework shows diverse training data improves subgroup and overall performance.
problem Lack of understanding how diverse training data affects subgroup and overall performance.
method Casts data collection as part of the learning process, analyzes dataset compositions, and guides dataset design.
result Diverse representation in training data improves subgroup and overall performance.
New method to quantify feature contributions to disparity without access to decision-making model.
problem Quantifying feature contributions to disparity when decision-making model is not accessible.
method Use information theory to measure redundant statistical dependency between protected attribute and feature.
result Quantify feature contributions to disparity using information theory.
Study evaluates when splitting classifiers can improve performance despite disparate treatment.
problem Impact of disparate treatment in classification models.
method Comparison of split classifiers and group-blind classifiers, quantifying performance improvement.
result Proves an equivalent expression for the benefit-of-splitting which can be efficiently computed.
Manifold matching works to identify embeddings of multiple disparate data spaces into the same low-dimensional space, where joint inference can be pursued. It is an enabling methodology for fusion and inference from multiple and massive disparate data sources. In this paper we focus on a method called Canonical Correla…
Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated dataset. The present paper extends the concept of optical flow estimation via co…