UBM transfers bias mitigation from upstream to downstream tasks efficiently.
problem Bias in fine-tuned language models across various tasks.
method Apply bias mitigation to an upstream model, then fine-tune a downstream model on this mitigated model.
result UBM effects transfer to new downstream tasks, creating less biased models.
This paper examines fairness and arbitrariness in bias mitigation methods.
problem Understanding how different bias mitigation strategies affect individual predictions and whether they introduce arbitrariness.
method FRAME framework to evaluate bias mitigation through five dimensions: Impact Size, Change Direction, Decision Rates, Affected Subpopulations, and Neglected Subpopulations.
result Significant differences in the behaviors of debiasing methods were exhibited, highlighting the limitations of current fairness criteria and the inherent arbitrariness in the debiasing process.
Study evaluates fairness of machine learning models on Kaggle and finds some optimization techniques can induce unfairness.
problem Ensuring fairness of machine learning models used in important decisions.
method Empirical evaluation of 40 top-rated models from Kaggle on 5 tasks, applying 7 mitigation techniques.
result Some model optimization techniques induce unfairness; mitigation in pre-processing is preferred.
This work identifies and mitigates reasoning shortcuts in Neuro-Symbolic models.
problem Neuro-Symbolic models can achieve high accuracy by using unintended concepts.
method Characterized reasoning shortcuts as unintended optima of the learning objective and identified four key conditions.
result Reasoning shortcuts are difficult to mitigate, casting doubt on NeSy solutions' trustworthiness and interpretability.
Model shows how discount rates affect intergenerational equity in climate mitigation.
problem Intergenerational equity in climate mitigation decisions.
method Extended DICE model with stochastic discount rates and financing extensions.
result Discount-rate uncertainty amplifies intergenerational inequality in climate mitigation.
Regularization methods can overregulate, suppressing causal features.
problem Mitigating shortcuts in models exploiting spurious correlations.
method Analysis of regularization methods and their effects on causal features.
result Regularization can overregulate, suppressing causal features.
Study evaluates bias mitigation methods in deep learning, finds they often exploit hidden biases.
problem Deep learning systems learn biases, affecting performance on minority groups.
method Improved evaluation protocol, new dataset, robustness across different tuning distributions.
result Bias mitigation methods often exploit hidden biases, are not robust to multiple forms of bias, and are sensitive to tuning set choice.
This paper describes the current taxonomy of model risk, ways for its mitigation and management and the importance of the model validation function in collaboration with other departments to design and implement them.
In this paper, we propose a new framework for mitigating biases in machine learning systems. The problem of the existing mitigation approaches is that they are model-oriented in the sense that they focus on tuning the training algorithms to produce fair results, while overlooking the fact that the training data can its…
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.
Recent developments have established the vulnerability of deep reinforcement learning to policy manipulation attacks via intentionally perturbed inputs, known as adversarial examples. In this work, we propose a technique for mitigation of such attacks based on addition of noise to the parameter space of deep reinforcem…
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.
New method mitigates bias without sensitive data using causal graph and variational autoencoder.
problem Lack of fairness strategies when sensitive attributes are not collected.
method SRCVAE framework based on causal graph for inferring a proxy sensitive attribute.
result Significant improvements in fairness metrics over existing methods.
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.
Study detects and mitigates stealthy DDoS attacks in IoT networks.
problem Stealthy DDoS attacks in IoT networks.
method Anomaly-based IDS for timely detection and mitigation.
result Demonstrated capability of detecting and mitigating small attack size per source.
This study analyzes bias in face generation models and proposes mitigation techniques.
problem Bias in face generation models that may misrepresent certain social groups.
method Three approaches: generators, attribute modifier, and post-processing bias mitigators.
result Generators suffer from bias across all social groups, while post-processing mitigators show different feature concentration.
New methods reduce bias in synthetic data for machine learning.
problem Statistical bias in synthetic data generated for privacy.
method Re-weighting strategies using privatised likelihood ratios.
result Private importance weighting enhances synthetic data utility.
Delusional bias is a fundamental source of error in approximate Q-learning. To date, the only techniques that explicitly address delusion require comprehensive search using tabular value estimates. In this paper, we develop efficient methods to mitigate delusional bias by training Q-approximators with labels that are "…
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.
Mitigates spurious correlations without bias labels.
problem Spurious correlations bias model performance.
method Introduces a novel training objective and debiasing method DPR.
result DPR achieves state-of-the-art performance.
Mitigates DeFi liquidations with reversible call options.
problem Systemic failures in DeFi due to liquidations.
method Introduces reversible call options to prevent liquidations.
result Reduces liquidated collateral by 89.82% in simulations.
fairmodels tool detects and mitigates bias in machine learning models.
problem Bias in machine learning models leading to discrimination.
method Model-agnostic approach to bias detection, visualization, and mitigation.
result Validates fairness and eliminates bias in classification models.
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.
Paper discusses how financial institutions' model risk management can benefit academic research.
problem Improving academic research process and mitigating limitations.
method Adopting financial institutions' model risk management practices.
result Lessons from financial institutions can enhance academic research reliability.
Voice-triggered smart assistants often rely on detection of a trigger-phrase before they start listening for the user request. Mitigation of false triggers is an important aspect of building a privacy-centric non-intrusive smart assistant. In this paper, we address the task of false trigger mitigation (FTM) using a nov…
Paper proposes synthetic data generator to study and mitigate bias in machine learning.
problem Bias in machine learning data can lead to unfair outcomes.
method Developed a synthetic data generator to introduce and analyze various types of bias.
result Demonstrated how synthetic data can be used to study and mitigate bias in machine learning models.
The study examines if enforcing fairness helps mitigate bias due to demographic shifts.
problem Bias in ML models due to underrepresented subpopulations in training data.
method Theoretical and simulation analysis of fairness enforcement in target domains.
result Enforcing fairness can lead to the Bayes model in the target domain under certain conditions.
This study simulates biases in classifiers to assess fairness.
problem Mitigating biases in predictive models to ensure fairness.
method Agent-based model (ABM) to generate synthetic datasets with controlled biases, applied to offline and online learning approaches.
result Demonstrates how biases in data affect classifier outcomes and how mitigations impact feature usage.
Generative multitask learning mitigates confounders causing targets.
problem Unobserved confounders causing targets but not inputs.
method Generative multitask learning (GMTL) modifies inference objective to remove joint target influence.
result Improved robustness to target shift across multitask learning methods.
Nowadays, advanced intrusion detection systems (IDSs) rely on a combination of anomaly detection and signature-based methods. An IDS gathers observations, analyzes behavioral patterns, and reports suspicious events for further investigation. A notorious issue anomaly detection systems (ADSs) and IDSs face is the possib…
AB dynamically scales gradients to mitigate asynchronous training delays.
problem Gradient delay in asynchronous training reduces model performance.
method Adaptive Braking (AB) dynamically scales gradients based on alignment.
result AB enables training with up to 32 update steps of delay without accuracy loss.
Deep networks can handle noisy labels up to a certain threshold.
problem Deep learning's robustness to noisy labels.
method Applying classical statistical theory and universal consistency of DNNs.
result Certain DNNs can tolerate massive symmetric label noise up to the information-theoretic threshold.
A robust loss for anomaly mitigation and unsupervised contamination classification
problem Detecting and mitigating contamination in supervised and unsupervised settings
method Neural Bayesian Anomaly Mitigation (NBAM)
result Recovering the structure of contamination and identifying label-flip pairs
Omega method mitigates noise in stochastic game optimization.
problem Noise sensitivity and convergence issues in stochastic game optimization.
method Omega method incorporates EMA of historic gradients in its update rule.
result Omega method outperforms optimistic gradient method in stochastic games.
Study characterizes and mitigates imbalances in neurosymbolic learning.
problem Characterizing and mitigating class-specific risks in neural classifiers.
method Theoretical analysis and practical techniques including estimating marginal gold labels and mitigating imbalances at training and testing time.
result Learning imbalances can be greatly impacted by the symbolic component σ, unlike in supervised and weakly supervised learning.
GraphTEE estimates treatment effects on graph-structured targets, mitigating bias.
problem Understanding treatment effects on graph-structured targets with observational bias.
method GraphTEE framework focusing on confounding variable sets and new regularization.
result GraphTEE mitigates bias better than previous methods.
MMbeddings reduces categorical embeddings by treating them as latent effects, significantly decreasing parameters and mitigating overfitting.
problem Large cardinalities in categorical embeddings lead to high parameter counts and overfitting.
method MMbeddings treats embeddings as latent random effects in a variational autoencoder framework, reducing parameter count and mitigating overfitting.
result MMbeddings consistently outperforms traditional embeddings across various tasks, demonstrating its potential in machine learning applications.
FairVIC improves fairness in neural networks without sacrificing accuracy.
problem Mitigating bias in automated decision-making systems, particularly in deep learning models.
method Integrates variance, invariance, and covariance terms into the loss function during training to abstract fairness concepts.
result Significant improvements in fairness across all tested metrics without compromising accuracy.
Propensity score matching improves fairness in machine learning models.
problem Bias in training data affects fairness metrics in machine learning models.
method Propensity score matching to evaluate and mitigate bias in test data.
result FairMatch significantly reduces bias in test data without sacrificing predictive performance.
Mitigates bias in weakly supervised datasets.
problem Bias in weakly supervised datasets.
method Proposes a counterfactual fairness-based technique to mitigate bias.
result Improves accuracy by up to 32% while reducing demographic parity gap by 82.5%.
Mathematical analysis shows annealing prevents mode collapse in Gaussian mixtures.
problem Mode collapse in variational inference for multimodal distributions.
method Analyzed annealing strategies for Gaussian mixtures, derived formulas, and tested on neural networks.
result Appropriately chosen annealing schemes can robustly prevent mode collapse.
Deep learning methods are widely regarded as indispensable when it comes to designing perception pipelines for autonomous agents such as robots, drones or automated vehicles. The main reasons, however, for deep learning not being used for autonomous agents at large scale already are safety concerns. Deep learning appro…
This paper tackles bias in federated learning without compromising data privacy.
problem Bias in federated learning models.
method Three pre-processing and in-processing methods to mitigate bias.
result Proposed methods are effective even with skewed data distributions or a small number of participating parties.
Adversarial examples in machine learning for images are widely publicized and explored. Illustrations of misclassifications caused by slightly perturbed inputs are abundant and commonly known (e.g., a picture of panda imperceptibly perturbed to fool the classifier into incorrectly labeling it as a gibbon). Similar atta…
Survey finds many adversarial machine learning threats are not critical for most entities.
problem Adversarial machine learning threats and their impact on model accuracy.
method Literature review and analysis of real-world occurrences of adversarial attacks.
result Many adversarial machine learning threats do not warrant the cost of robust models.
Study explores D-Wave QA for RBM training, finds modest benefits but no significant improvements.
problem Improving RBM training using D-Wave quantum annealing.
method Hybrid sampling approach combining classical and D-Wave QA methods.
result No significant improvements in RBM training using D-Wave QA, but potential for CF mitigation.
Whereas previous post-processing approaches for increasing the fairness of predictions of biased classifiers address only group fairness, we propose a method for increasing both individual and group fairness. Our novel framework includes an individual bias detector used to prioritize data samples in a bias mitigation a…
FVNNs use graph convolutions on fair covariance estimates to improve fairness in machine learning.
problem Data-driven methods can encode biases in sample covariance matrices, leading to unfair treatment of different subpopulations.
method FVNNs perform graph convolutions on fair covariance estimates and use a fairness regularizer in the loss function.
result FVNNs provide a flexible model that is intrinsically fairer than PCA approaches and can handle low sample regimes.