New method corrects skewed confidence for PbN classification.
problem Weakly supervised binary classification with biased negative data.
method Corrects skewed confidence in negative data to improve classifier.
result Reduces distortion in posterior probability for PbN classification.
Paper tackles binary classification with biased negative data.
problem Binary classification with diverse negative data and biased negative data.
method Empirical risk minimization method with example weighting.
result Effective in PUbN and PU learning scenarios.
Regularized training of an autoencoder typically results in hidden unit biases that take on large negative values. We show that negative biases are a natural result of using a hidden layer whose responsibility is to both represent the input data and act as a selection mechanism that ensures sparsity of the representati…
Fairness constraints can improve accuracy from biased data.
problem Learning from biased training data can produce biased and suboptimal classifiers.
method Examined fairness-constrained ERM and other recovery methods.
result Equal Opportunity fairness constraint combined with ERM provably recovers Bayes Optimal Classifier under various bias models.
The paper tackles bandit problems with biased offline data by using causal methods.
problem Improving bandit algorithms with biased offline data that includes confounding and selection biases.
method Formalizes the problem from a causal perspective, categorizes biases, and derives robust bounds for each arm.
result Causal bounds can guide the bandit agent to learn a nearly-optimal decision policy and consistently reduce asymptotic regret.
The study examines how social biases are reinforced in machine learning models used for credit scoring.
problem Reinforcement of societal biases in machine learning algorithms for credit scoring.
method Analysis of machine learning models predicting gender or ethnicity based on loan applications data.
result Machine learning models can reflect and reinforce social biases present in the data.
New method improves model robustness to biased data.
problem Learning unbiased models from biased datasets.
method Developed epsilon-SupInfoNCE and FairKL losses.
result Improved performance on biased datasets.
New theory shows how learning algorithms can create a bias towards negative outcomes.
problem Negativity bias in adaptive learning algorithms.
method Generalization of the Hot Stove Effect to settings with negative estimates leading to smaller sample sizes.
result Negativity bias persists even when negative estimates do not lead to avoidance.
This paper proposes a new method to use unlabeled data as positive data, improving PU learning.
problem Improving positive-unlabeled learning methods in deep learning.
method Labeling large-loss unlabeled data as positive data and developing a new learning objective.
result The proposed method outperforms the latest importance reweighting method in experiments.
We provide a mathematical definition of fragility and antifragility as negative or positive sensitivity to a semi-measure of dispersion and volatility (a variant of negative or positive "vega") and examine the link to nonlinear effects. We integrate model error (and biases) into the fragile or antifragile context. Unli…
Paper detects biases in medical imaging ML models using counterfactual analysis.
problem Bias in medical imaging ML models negatively impacts generalization performance.
method Counterfactual invariance framework combining conditional latent diffusion models and statistical hypothesis testing.
result The method identifies and quantifies biases without direct access to counterfactual data.
Paper connects sampling and labeling biases in large-output spaces.
problem Efficient training in large-output spaces with label imbalance.
method Unified approach to address sampling and labeling biases.
result Different negative sampling schemes trade-off performance on dominant and rare labels.
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.
A new method removes biases in data integration by using surrogate control outcomes.
problem Data integration methods can be biased due to data-dependent processes.
method Post-integrated inference method using surrogate control outcomes to account for latent heterogeneity.
result The method provides consistent and efficient estimators under minimal assumptions and potential misspecifications.
Bayesian relabeling improves PU learning for biased positive examples.
problem Learning from biased positive examples in PU learning.
method Probabilistic-gap based PU learning with Bayesian optimal relabeling and kernel mean matching.
result The proposed algorithm improves performance on real-world datasets.
Proposes a method to train classifiers with delayed feedback using a time window.
problem Training classifiers with delayed feedback that can be biased due to delayed user actions.
method Uses a time window to select samples for training, constructs unbiased empirical risk from all samples.
result Improves classifier performance by using all samples with a time window assumption.
From scientific experiments to online A/B testing, the previously observed data often affects how future experiments are performed, which in turn affects which data will be collected. Such adaptivity introduces complex correlations between the data and the collection procedure. In this paper, we prove that when the dat…
This paper debiases KG embeddings by filtering sensitive attributes.
problem Social and cultural biases in KG representations.
method Exploring and filtering popularity and gender biases in KGE.
result Sensitivity of KG embeddings to sensitive attributes like gender.
Study shows it's hard to detect when a decision-maker fakes fairness using a specific sampling technique.
problem Detecting when decision-makers fake fairness using auditing tools.
method Developed a stealthily biased sampling algorithm to construct deceptive benchmark datasets.
result The constructed deceptive datasets are difficult to detect, making it hard to avoid fake fairness.
RS-PINN uses randomized smoothing to speed up high-dimensional PDE simulations without sacrificing accuracy.
problem High computational cost and bias in PINNs for high-dimensional PDEs.
method Introduces Gaussian noise for stochastic smoothing of PINNs, enabling Monte Carlo derivative approximation.
result Proposes bias correction techniques and a hybrid method to optimize the bias-variance trade-off.
Machine learning models predict brain age with systematic bias, corrected in this study.
problem Systematic bias in machine learning regression models for brain age prediction.
method General constrained optimization approach to correct bias.
result Our method effectively eliminates the bias from brain age predictions.
This paper evaluates debiasing methods on word embeddings to reduce religious bias.
problem Social biases persist in word embeddings, potentially amplifying them in AI applications.
method Investigates and evaluates three multiclass debiasing techniques on three word embeddings.
result ConceptorDebiasing is the most effective method, reducing religious bias by 82-96%.
Social media reduces individual investors' disposition effect through negative information.
problem The disposition effect in individual investors selling profitable assets too early and holding onto losing assets for too long.
method Analysis of post data and trading data from Xueqiu.com.
result Social media information significantly reduces the disposition effect.
WEINCE improves contrastive learning by correcting softmax biases.
problem Softmax in InfoNCE can lead to misaligned statistical assumptions in contrastive learning.
method WEINCE uses anchor-wise online batch statistics to blend softmax logits with an endpoint shortfall correction.
result WEINCE yields consistent improvements in frozen-feature evaluation across five vision benchmarks.
Tree-based models biased when trained on imbalanced data, requiring new calibration methods.
problem Bias in tree-based models trained on imbalanced datasets.
method Analytical calibration of random forest models, demonstrating bias in decision trees.
result Calibrating tree-based models on imbalanced data negatively impacts predictions, especially for the minority class.
Conventional collaborative filtering techniques treat a top-n recommendations problem as a task of generating a list of the most relevant items. This formulation, however, disregards an opposite - avoiding recommendations with completely irrelevant items. Due to that bias, standard algorithms, as well as commonly used …
A common approach in positive-unlabeled learning is to train a classification model between labeled and unlabeled data. This strategy is in fact known to give an optimal classifier under mild conditions; however, it results in biased empirical estimates of the classifier performance. In this work, we show that the typi…
Machine learning confound removal biases results, leading to misleading predictions.
problem Common confound removal methods in machine learning lead to misleading predictions.
method Featurewise removal of confound variance by linear regression before applying ML.
result This common deconfounding approach can leak information, amplifying null or moderate effects.
We study a sparse negative binomial regression (NBR) for count data by showing the non-asymptotic advantages of using the elastic-net estimator. Two types of oracle inequalities are derived for the NBR's elastic-net estimates by using the Compatibility Factor Condition and the Stabil Condition. The second type of oracl…
ReLU networks implicitly favor low-rank solutions, but not as strongly as linear networks.
problem Understanding implicit regularization in ReLU networks for rank minimization.
method Analysis of gradient flow on ReLU networks, empirical testing.
result Gradient flow on ReLU networks does not necessarily minimize ranks, unlike in linear networks.
Protein-protein interaction (PPI) prediction is an important problem in machine learning and computational biology. However, there is no data set for training or evaluation purposes, where all the instances are accurately labeled. Instead, what is available are instances of positive class (with possibly noisy labels) a…
This paper examines biases in foundation models under long-tailed data and proposes a method to mitigate parameter imbalance.
problem The bias introduced by imbalanced training data in foundation models affects long-tailed downstream tasks.
method The paper examines parameter imbalance and data imbalance, proposing a backdoor adjustment method to mitigate parameter imbalance.
result An average performance increase of about 1.67% on each dataset.
Paper explores how knowledge distillation transfers inductive biases between models.
problem Transferring inductive biases between models for tasks with limited data.
method Knowledge distillation applied to models with different inductive biases (LSTMs vs. Transformers, CNNs vs. MLPs).
result Effect of inductive biases is transferred through knowledge distillation, impacting both performance and solution characteristics.
In many classification systems, sensing modalities have different acquisition costs. It is often {\it unnecessary} to use every modality to classify a majority of examples. We study a multi-stage system in a prediction time cost reduction setting, where the full data is available for training, but for a test example, m…
New metrics improve scRNA-seq perturbation modeling by reducing mode collapse.
problem Outperformed by simple mean prediction in scRNA-seq perturbation modeling.
method Introduce DEG-aware metrics (WMSE, Rw2(Δ)) and negative/positive baselines. result WMSE loss function reduces mode collapse and improves model performance.
Analyze SGD with biased gradients, improving convergence rates and accuracy.
problem Analyzing the convergence of SGD with biased gradients.
method Derive convergence results for smooth non-convex functions and quantify the impact of bias magnitude.
result Improved rates under the Polyak-Lojasiewicz condition and insights into how bias magnitude affects accuracy and convergence.
The paper analyzes bias in sample means of multi-armed bandits.
problem Analyzing bias in sample means of multi-armed bandits.
method Decoupling three sources of bias: sampling, stopping, choosing; using optimism to capture monotonic behaviors.
result Optimistic sampling induces negative bias, while optimistic stopping and choosing induce positive bias.
New method discourages models from using bias shortcuts for better generalization.
problem Training models on biased data can lead to poor generalization when bias shifts.
method Train a de-biased representation by encouraging it to differ from biased representations.
result Improved generalization across synthetic and real-world biases.
Unified diffusion model tackles missing data in tabular datasets.
problem Training diffusion models on tabular data with missing values.
method Proposes a masked regression loss for Denoising Score Matching to learn from incomplete data.
result Demonstrates superior performance on tabular datasets with missing values compared to state-of-the-art methods.
Machine learning biases in job recommendations can lead to unfair outcomes.
problem Biased recommendations from recommender systems in job matching.
method Addressing biases at various stages of recommender systems training and deployment.
result Techniques can reduce bias in job recommendations, ensuring fair outcomes.
Gradient-based methods can be biased by distributional asymmetries in bivariate categorical data.
problem Gradient-based causal discovery methods can be biased by distributional asymmetries in bivariate categorical data.
method Identified and examined two distributional biases: Marginal Distribution Asymmetry and Marginal Distribution Shift Asymmetry. Employed two simple models to demonstrate and control these biases.
result Gradient-based methods can be biased by distributional asymmetries, and these biases can be controlled.
Study shows statistical biases can mislead transformer models, impairing their generalization.
problem Statistical biases in transformers affect their ability to generalize.
method Evaluated transformer models on synthetic algorithmic tasks with varying statistical biases.
result Statistical biases lead to overestimation of transformer models' generalization capabilities.
New method corrects seasonal Arctic sea ice predictions with probabilistic models.
problem Systematic biases and errors in climate model forecasts of Arctic sea ice.
method Conditional Variational Autoencoder model to map observation distribution given biased model predictions.
result Probabilistic adjusted forecasts are better calibrated and have smaller errors.
New oracles improve stochastic optimization with noisy or biased measurements.
problem Optimizing functions with noisy or biased measurements.
method Introduced biased gradient oracles for stochastic optimization, analyzed RSG and SGD algorithms with these oracles.
result Derived non-asymptotic bounds for convergence rates of algorithms with biased gradient oracles.
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).
Study reveals biases in ImageNet models are not sufficient for generalization.
problem Understanding and improving generalization of image classification models.
method Large-scale study of 48 ImageNet models trained via various methods.
result Biases identified in ImageNet models do not fully explain generalization.
The positive-unlabeled (PU) classification is a common scenario in real-world applications such as healthcare, text classification, and bioinformatics, in which we only observe a few samples labeled as "positive" together with a large volume of "unlabeled" samples that may contain both positive and negative samples. Bu…
Study examines whether biased training data lead to biased algorithms.
problem Tackles the issue of bias in algorithmic decision-making.
method Examines a setting where biased human decision-makers affect training data and labels.
result Clarifies conditions for bias reversal in algorithmic decision rules.