Paper compares dimensionality reduction methods for affect classification.
problem Difficulty in obtaining labeled training samples for affect classification.
method Five dimensionality reduction approaches are compared.
result No single approach universally outperforms others in affect classification.
The paper examines how algorithmic classification affects behavior and proposes democratizing stakes to mitigate predatory practices.
problem The impact of algorithmic classification on individual behavior and fairness in decision-making processes.
method Characterization of optimal classification by an algorithm designer and analysis of the effect of democratizing stakes.
result Optimal classification can lead to surprising behavior patterns, and democratizing stakes can mitigate predatory practices.
This work applies deep learning to bio-sensing and video data for affective computing.
problem Lack of deep learning integration in bio-sensing for affective computing.
method Novel deep-learning-based methods applied to EEG, ECG, and video data.
result Outperforms other studies in emotion/valence/arousal/liking classification.
Study shows how correlations between neural activity affect classification capacity.
problem Understanding how correlations between neural activity impact classification performance.
method Calculated the capacity of neural activity on spherical manifolds with and without correlations between centroids and axes.
result Introducing correlations between neural activity centroids pushes spheres closer together, while correlations between axes shrink their radii, revealing a duality between correlations and geometry in classification.
Study examines how digital image alterations affect AI classification models.
problem Impact of digital alterations on image classification models.
method Evaluation of state-of-the-art machine learning models under various digital image alterations.
result Discoveries in training techniques to enhance model robustness.
Study examines how uncertainty visualization affects analyst trust in automated classification systems.
problem The impact of uncertainty on analyst trust in automated classification systems.
method Empirical study evaluating different active learning query policies and visualizations.
result Query policy significantly influences analyst trust in automated classification systems.
This paper uses GANs to generate synthetic Bitcoin address data.
problem Class imbalance in Bitcoin ground-truth datasets affects supervised machine learning results.
method Generative Adversarial Networks (GANs) for synthetic data generation.
result A 'good' GAN configuration can be found to generate synthetic Bitcoin address data with high similarity to real data.
The study examines how class imbalance impacts logistic regression models in low-default credit portfolios.
problem The impact of class imbalance on logistic regression models in low-default credit portfolios.
method Simulation study with controlled data-generating mechanisms to vary class imbalance and predictor-response association strength.
result Classification accuracy decreases significantly as event rate decreases, and optimal cut-off shifts with imbalance.
The paper offers tools to ensure people can change automated loan decisions.
problem People should be able to alter input variables to avoid being denied loans.
method Integer programming tools for linear classification problems.
result Recourse can be significantly affected by standard model development practices.
DeepJet improves jet flavor classification and quark-gluon tagging.
problem Jet flavor classification in high-energy physics experiments.
method Proposes a novel deep learning architecture, DeepJet, for improved performance.
result Improves heavy flavor classification performance and extends to quark-gluon tagging.
Study identifies pitfalls in assessing hierarchies for multi-class classification.
problem Lack of understanding in selecting hierarchies for multi-class classification.
method Analyzed and compared popular approaches to extracting hierarchies.
result Hierarchy quality becomes irrelevant when using powerful classifiers.
Few-shot image classification is improved by correcting CNNs' texture bias.
problem Few-shot image classification performance is hindered by CNNs' texture bias.
method Corrected CNNs' texture bias using a simpler method than state-of-the-art approaches.
result State-of-the-art performance on miniImageNet task achieved.
The paper investigates AI robustness through experiments and statistical analysis.
problem Inaccurate AI predictions can lead to safety and adoption issues.
method Design of experiments framework to study AI classification robustness.
result AI algorithms' robustness is influenced by various factors.
Debiasing techniques can worsen gender bias in text classification, but a tweak improves both.
problem Debiasing techniques can inadvertently increase gender bias in text classification.
method Investigated traditional debiasing techniques and found they worsen bias. Suggested a minor adjustment.
result A minor adjustment to debiasing techniques can reduce gender bias while maintaining high classification accuracy.
SVHN dataset's split affects generative models but not digit classification.
problem Distribution mismatch between SVHN training and test sets impacts generative models.
method Empirically showed distribution mismatch affects generative models; proposed mixing and re-splitting.
result Distribution mismatch in SVHN dataset significantly impacts probabilistic generative models.
Reduces gender classification bias by learning race-invariant face representations.
problem Societal bias in gender recognition systems.
method Adversarially trained autoencoder model to learn race-invariant face representations.
result Achieved a significant drop of over 40% in racial bias surrogate metric with race invariant representations.
Bayesian neural networks' performance varies with prior choice, affecting their ability to identify unknowns.
problem The impact of prior choice on Bayesian neural networks' ability to identify unknowns.
method Evaluation of different prior distributions on classification tasks using BNNs and NNs with Monte Carlo dropout.
result Prior choice significantly impacts BNNs' ability to identify unknowns, affecting true and false positive rates.
The study estimates how changing words in sentences affects audience perception.
problem Estimating the causal effect of lexical choice on audience perception.
method Two classes of methods: quasi-experimental designs and classification problems.
result Algorithmic estimates align with randomized-control trials and can be transferred across domains.
A new algorithm reduces imbalanced data classification errors in multi-class settings.
problem Imbalanced data classification, especially with noise and overlapping classes.
method MC-CCR algorithm combining cleaning and resampling.
result High robustness to noise and superior performance compared to state-of-the-art methods.
Detects drifts in data for classification tasks using constrained embeddings.
problem Drifts in data affect model performance; unsupervised methods ignore label information.
method Task-sensitive semi-supervised drift detection with constrained low-dimensional embedding.
result Successfully detects real drifts affecting classification performance.
Proposes a method to increase diversity without sacrificing meritocracy.
problem Systemic bias in datasets affecting diversity and meritocracy.
method Optimally flipping outcome labels and training classification models simultaneously.
result The price of diversity is low and sometimes negative, enhancing diversity without significantly affecting meritocracy.
Rewiring edges subtly improves graph neural networks' robustness.
problem Vulnerability of graph neural networks to subtle structural perturbations.
method Proposes a graph rewiring operation and uses reinforcement learning to learn attack strategies.
result Demonstrates the effectiveness of the proposed framework on real-world graphs.
Unified framework for imbalanced data resampling improves classification performance.
problem Data imbalance negatively impacts machine learning performance.
method Unified framework combining over- and undersampling with radial basis functions optimization.
result Potential Anchoring outperforms state-of-the-art resampling algorithms.
Study examines how balancing methods affect model behavior in imbalanced classification problems.
problem Impact of balancing methods on model behavior in imbalanced classification problems.
method Used Explainable Artificial Intelligence tools (variable importance method, partial dependence profile, accumulated local effects) to compare model behavior before and after balancing.
result Significant changes in model behavior due to balancing methods, leading to biased models.
Paper analyzes factors affecting COVID-19 risk in US counties.
problem Identifying factors influencing COVID-19 risk in US counties.
method Combines unsupervised (K-means clustering) and supervised learning models.
result Mean temperature, poverty, obesity, and other factors are most significant.
New algorithms handle missing data to improve fairness in machine learning.
problem Missing values in data can lead to unfair outcomes in machine learning models.
method Developed scalable and adaptive algorithms to handle missing values while preserving predictive information.
result Our adaptive algorithms consistently achieve higher fairness and accuracy than standard impute-then-classify methods.
We propose a voted dual averaging method for online classification problems with explicit regularization. This method employs the update rule of the regularized dual averaging (RDA) method, but only on the subsequence of training examples where a classification error is made. We derive a bound on the number of mistakes…
Changing initialization scale affects deep model generalization, leading to memorization or improved performance.
problem Understanding how initialization scale impacts deep model generalization and memorization.
method Experimental setup with varying initialization scales, analysis of activation and loss functions, and development of an alignment measure.
result Increasing initialization scale leads to memorization, and decreasing it improves generalization, depending on activation and loss functions.
This paper examines how graph topology affects adversarial attacks on vertex classification.
problem Adversarial attacks on vertex classification are vulnerable to graph topology changes.
method Examined two topological graph characteristics and their impact on adversary perturbation budgets.
result Training sets including high-degree vertices or those ensuring all unlabeled nodes have neighbors can significantly increase the adversary's perturbation budget.
The difficulty of classification affects the weight matrices' heavy tail appearance in deep learning networks.
problem Understanding the spectral properties of weight matrices in deep learning networks.
method Spectral analysis of weight matrices in different modules of DNNs, classification difficulty as a driving factor for heavy tail appearance.
result Higher classification difficulty leads to more frequent appearance of heavy tails in weight matrices spectra.
Study shows how bias in optimization affects robustness in adversarial settings.
problem Understanding and mitigating implicit bias in adversarially robust models.
method Analyzes the implicit bias in robust empirical risk minimization and its impact on generalization.
result Implicit bias in optimization can significantly affect robust generalization.
We adapt the idea of random projections applied to the output space, so as to enhance tree-based ensemble methods in the context of multi-label classification. We show how learning time complexity can be reduced without affecting computational complexity and accuracy of predictions. We also show that random output spac…
Cost-effective feature selection improves network model choice.
problem Selecting informative features from noisy candidates in network models.
method Adapted feature selection methods to account for feature costs and used pilot simulations.
result Reduced computational cost by two orders of magnitude without sacrificing model accuracy.
New feature representation improves HAR model accuracy.
problem Improving human activity recognition model performance.
method Proposed new feature representation and comparison with existing methods.
result Techniques based on the proposed representation outperform baselines.
This work examines how non-identical data distributions affect Federated Learning performance.
problem The impact of non-identical data distributions on Federated Learning performance.
method Synthesized datasets with varying degrees of data distribution similarity, evaluated Federated Averaging algorithm performance, proposed server momentum mitigation.
result Performance of Federated Learning degrades as data distributions differ more, and a mitigation strategy improves accuracy.
Privacy affects fairness in classification models, but not drastically.
problem The impact of differential privacy on fairness in classification models.
method Theoretical analysis proving Lipschitz continuity of fairness measures and a non-asymptotic bound on fairness levels.
result Privacy impacts fairness, but not significantly as the number of samples increases.
Ensembles of classifier models typically deliver superior performance and can outperform single classifier models given a dataset and classification task at hand. However, the gain in performance comes together with the lack in comprehensibility, posing a challenge to understand how each model affects the classificatio…
The paper examines how social inequality affects algorithmic classification outcomes.
problem Social inequality impacts algorithmic classification outcomes.
method Adapting models of strategic manipulation to account for social inequality and subsidy effects.
result Subsidizing disadvantaged groups can paradoxically harm both groups and the learner.
Bayesian method improves reliability of BERT for hate speech detection.
problem Reliable detection of hate speech in user-generated content.
method Bayesian approach using Monte Carlo dropout in transformer models.
result Monte Carlo dropout provides well-calibrated reliability estimates.
Proposes a framework for balancing fairness and accuracy in data-restricted binary classification.
problem Balancing fairness and accuracy in applications with data restrictions.
method Directly analyzes the optimal Bayesian classifier's behavior under different data-restricting scenarios, formulating convex optimization problems.
result Demonstrates how accuracy of a Bayesian classifier is affected by fairness constraints in various data-restricting scenarios.
Paper defends iris recognition from adversarial examples using wavelet decomposition.
problem Adversarial examples threaten deep neural networks in biometric applications.
method Wavelet domain denoising of input examples to detect and mitigate adversarial attacks.
result Proposed defense strategies improve recognition accuracy against adversarial attacks.
Improved VAE representations lead to better image classification.
problem VAE representations are inferior to non-latent models for image classification.
method Used a decoder that prefers local features, improving global feature capture in latent variables.
result Significant improvement in downstream semantic classification tasks.
New methods for handling time-varying label noise in time series classification.
problem Temporal label noise in time series classification tasks.
method Proposed methods to estimate temporal label noise function directly from data.
result Our methods lead to state-of-the-art performance under diverse types of temporal label noise.
This paper examines how adversarial perturbations affect model performance and equilibrium learning.
problem Adversarial perturbations and covariate shifts impact model performance and equilibrium learning.
method Characterizes the extrapolation region in regression and classification, analyzes dynamics of adversarial learning games.
result Establishes two directional convergence results: a blessing in regression and a curse in classification.
Machine learning classifies colorectal tissue using photoacoustic microscopy.
problem Traditional diagnostic methods for colorectal cancer are limited in detail and painful.
method Machine learning applied to acoustic resolution photoacoustic microscopy.
result Machine learning accurately classified benign and malignant tissue.
The study classifies policy announcements' impact on stock market volatility.
problem Evaluating the impact of Central Bank announcements on stock market volatility.
method Proposed a model-based classification method using Markov Switching dynamics and Multiplicative Error Model.
result Successful classification of 144 European Central Bank announcements on stock market volatility.
Novel IndRNN model improves seizure/non-seizure classification accuracy.
problem Manual EEG analysis by neurologists is laborious and prone to errors.
method Leverages independently recurrent neural networks (IndRNN) to capture seizure features across various time scales.
result The proposed approach outperforms state-of-the-art methods in cross-validation experiments.
In this paper, we investigate the multi-variate sequence classification problem from a multi-instance learning perspective. Real-world sequential data commonly show discriminative patterns only at specific time periods. For instance, we can identify a cropland during its growing season, but it looks similar to a barren…