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.
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…
Survey on fake news identification and mitigation techniques.
problem Proliferation of fake news on social media impacts public opinion.
method Identification and mitigation techniques, focusing on content and user engagement.
result Significant advances in identification and mitigation methods.
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.
Mitigates faults in DNNs by clipping activation values, improving their resilience.
problem Fault tolerance of DNNs in safety-critical applications.
method Clipping activation functions to reduce impact of faulty weights.
result Significant improvement in classification accuracy (68.92%) for fault mitigation.
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%.
Survey of methods to reduce false alarms in IDSs and ADSs.
problem High false alarms in IDSs and ADSs overwhelm administrators.
method Customized anomaly scoring and filtering methods.
result Promising techniques for reducing false alarms exist.
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.
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.
Machine learning improves fiber nonlinearity detection.
problem Mitigating nonlinear effects in optical fiber channels.
method Parzen window classifier applied to detect nonlinear fiber channel.
result Performance improvement in dispersion managed and unmanaged systems.
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.
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.
This paper explores security threats in ML systems and proposes mitigation techniques.
problem Security vulnerabilities in ML-based systems during training and inference.
method Overview of security threats, demonstrations using LeNet and VGGNet, proposed attack.
result Demonstrated security threats and proposed mitigation techniques.
Particle Markov chain Monte Carlo techniques rank among current state-of-the-art methods for probabilistic program inference. A drawback of these techniques is that they rely on importance resampling, which results in degenerate particle trajectories and a low effective sample size for variables sampled early in a prog…
This paper analyzes how differential privacy and data skewness affect membership inference attacks.
problem Membership inference attacks on privately trained models.
method Developed MPLens system to evaluate membership inference vulnerability.
result Membership inference risk is higher with skewed training data and differential privacy has trade-offs.
ReLU networks often give high confidence far from training data, new technique mitigates this.
problem ReLU networks produce high confidence predictions far from training data, which is undesirable.
method Proposed a new robust optimization technique similar to adversarial training to enforce low confidence predictions.
result The technique reduces confidence of predictions far from training data while maintaining test error on the original task.
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.
ConQUR tackles delusional bias in deep Q-learning, improving performance in Atari games.
problem Delusional bias in deep Q-learning.
method Efficient methods to mitigate delusional bias by training Q-approximators with consistent labels and a search framework.
result Improves performance in Atari games, sometimes dramatically.
New approach uses deep learning to control SAI for climate mitigation.
problem Catastrophic regional consequences of naive SAI control.
method Treats SAI as a high-dimensional control problem using Deep Reinforcement Learning (DRL).
result First application of DRL to climate sciences.
Models to price long term loans in the securities lending business are developed. These longer horizon deals can be viewed as contracts with optionality embedded in them. This insight leads to the usage of established methods from derivatives theory to price such contracts. Numerical simulations are used to demonstrate…
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.
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.
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.
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.
FairLangProc simplifies fairness in NLP models for Python users.
problem Addressing bias in NLP models for decision-making contexts.
method Develops a Python package for implementing fairness metrics and algorithms.
result Promotes the use of bias mitigation techniques in NLP.
Survey on privacy issues in deep learning and proposed solutions.
problem Privacy concerns in deep learning models due to sensitive data.
method Review of existing privacy techniques and gaps in research.
result Identification of test-time inference privacy as a research gap.
Bayesian optimization framework for fair machine learning models.
problem Bias in machine learning models and lack of adaptability of fairness techniques.
method General constrained Bayesian optimization framework.
result BO can optimize ML models for fairness without model-specific constraints.
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.
Optimizes wireless power control using graph neural networks and counterfactual optimization.
problem Mitigating interference in wireless networks with multiple transmitter-receiver pairs.
method Graph neural network architecture combined with unsupervised primal-dual counterfactual optimization.
result Guarantees a minimum rate constraint that adapts to network size, balancing user rates.
Machine Learning (ML) is making a strong resurgence in tune with the massive generation of unstructured data which in turn requires massive computational resources. Due to the inherently compute- and power-intensive structure of Neural Networks (NNs), hardware accelerators emerge as a promising solution. However, with …
New algorithm mitigates affinity bias in hiring feedback loops.
problem Mitigating affinity bias in hiring decisions to avoid unconscious favoritism.
method Introducing affinity bandits, a new bandit variant that accounts for evolving biased feedback.
result Elimination-style algorithm nearly matches the derived regret bound, outperforming classical algorithms.
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.
Framework uses dropout to efficiently explore Rashomon set for multiplicity estimation.
problem Efficiently measuring and mitigating conflicting model outputs in classification tasks.
method Dropout-based exploration of Rashomon set for multiplicity estimation.
result Framework outperforms baselines in multiplicity metric estimation with significant runtime speedup.
Automatic continuous speech recognition (CSR) is sufficiently mature that a variety of real world applications are now possible including large vocabulary transcription and interactive spoken dialogues. This paper reviews the evolution of the statistical modelling techniques which underlie current-day systems, specific…
Mitigates biases in reward models using variational inference.
problem Spurious correlations in reward models that align large language models with human preferences.
method Formulates data-generating process, identifies non-spurious latent variables, and uses variational inference to recover them.
result Effective mitigation of spurious correlation issues, yielding more robust reward models.
Machine learning is vulnerable to adversarial examples: inputs carefully modified to force misclassification. Designing defenses against such inputs remains largely an open problem. In this work, we revisit defensive distillation---which is one of the mechanisms proposed to mitigate adversarial examples---to address it…
New algorithm mitigates misspecification amplification in regression models with covariate shift.
problem Distribution shift and model misspecification in regression models.
method Developed a new algorithm inspired by robust optimization to avoid misspecification amplification.
result No misspecification amplification while still achieving optimal statistical rates.
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.
Improved optimization technique reduces training complexity for non-convex problems.
problem Training non-convex optimization problems with exploding gradients.
method Employed variance reduction technique (SPIDER) with carefully designed learning rate.
result Improved stochastic gradient complexity to O(ε−3) for ε-stationary solutions. The paper introduces a framework for prescriptive process monitoring that generates alarms to prevent or mitigate undesired outcomes.
problem Existing predictive process monitoring techniques do not prescribe when and how to intervene to decrease undesired outcomes.
method The paper proposes a framework that extends predictive monitoring with the ability to generate alarms, incorporating a cost model to assess the trade-off between generating alarms and the cost of undesired outcomes.
result The net cost of undesired outcomes can be minimized by optimizing the generation of alarms based on the progress of the process instance and introducing delays for triggering alarms.
Improves domain adaptation by aligning source and target distributions and mitigating noisy labels.
problem Improving performance on target images with different acquisition conditions.
method Combines optimal transport, MixUp regularization, and robust loss for noisy labels.
result Improves domain adaptation performance on various benchmarks and real-world problems.
We propose a numerical algorithm for backward stochastic differential equations based on time discretization and trigonometric wavelets. This method combines the effectiveness of Fourier-based methods and the simplicity of a wavelet-based formula, resulting in an algorithm that is both accurate and easy to implement. F…
The paper tackles intersectional fairness in machine learning, proposing methods to assess and mitigate bias.
problem Achieving optimal predictive performance is not enough; fairness with respect to multiple sensitive attributes is crucial.
method The paper introduces a comprehensive framework for auditing and achieving intersectional fairness in classification problems, including metrics, estimation methods, and post-processing techniques.
result The proposed methods can robustly estimate and mitigate intersectional bias in classification models without compromising predictive performance.
Machine learning in high-energy physics faces challenges from nuisance parameters, which are reviewed and techniques to mitigate their impact are discussed.
problem Impact of nuisance parameters on machine learning performance in high-energy physics.
method Review and discussion of techniques including nuisance-parameterized models, modified or adversary losses, semi-supervised learning, and inference-aware techniques.
result Various methods to reduce the impact of nuisance parameters and improve model performance in high-energy physics.
Framework improves fairness in machine learning models using adversarial techniques.
problem Unfair decision processes in machine learning models.
method Two-step framework involving fairness optimization and evasion attacks.
result Framework significantly improves fairness metrics on tested datasets.
This paper offers a mathematical framework to manage inventory risk in FX cash markets.
problem Inventory risk in FX cash markets due to flow uncertainty and volatility.
method Mathematical framework and approximation techniques for scalability.
result Maximizing expected profit while controlling inventory risk.
New techniques exploit market systems to manipulate prices.
problem Market manipulation through technical details and glitches.
method Analyzed and modeled market manipulation techniques and proposed mitigation measures.
result Technical solutions can significantly thwart market manipulation.
New method reduces copyright risks in AI-generated images.
problem Copyright issues in AI-generated images.
method Genericization method using originality estimation and PREGen technique.
result PREGen reduces likelihood of generating copyrighted characters by over half.