Datasets often contain biases which unfairly disadvantage certain groups, and classifiers trained on such datasets can inherit these biases. In this paper, we provide a mathematical formulation of how this bias can arise. We do so by assuming the existence of underlying, unknown, and unbiased labels which are overwritt…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “biased 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.
Solves biased pseudo-labels in imbalanced SSL by refining them.
problem Imbalanced class distributions in semi-supervised learning lead to biased pseudo-labels.
method Formulates a convex optimization problem to refine pseudo-labels and develops an efficient algorithm, DARP.
result Demonstrates the effectiveness of DARP in various imbalanced semi-supervised scenarios.
In this paper, we study the classification problem in which we have access to easily obtainable surrogate for true labels, namely complementary labels, which specify classes that observations do \textbf{not} belong to. Let and be the true and complementary labels, respectively. We first model the annotati…
GCNs favor high-degree nodes, leading to biased performance; a new method mitigates this.
problem Degree-related biases in GCNs, especially for low-degree nodes.
method Developed a novel SL-DSGC that reduces model and data biases.
result SL-DSGC improves GCN accuracy significantly for low-degree nodes.
Active learning suffers from biased non-response, which this paper addresses.
problem Active learning's effectiveness is compromised by biased non-response in real-world contexts.
method Proposes a cost-based correction to the sampling strategy, UCB-EU, to mitigate the impact of biased non-response.
result UCB-EU successfully reduces the harm from labelling non-response in many settings.
InfoSEM: A Deep Generative Model with Informative Priors for Gene Regulatory Network Inferencestat.ML
InfoSEM infers gene regulatory networks without GT labels, improving performance.
problem Inferring GRNs from gene expression data with high accuracy and avoiding biases.
method InfoSEM uses deep generative models with informative priors (textual gene embeddings).
result InfoSEM outperforms existing models by 38.5% across four datasets.
Paper proposes using unlabeled data for fair decision-making.
problem Bias in decision-making algorithms due to biased labels and selective labeling.
method Variational autoencoder for learning unbiased data representations from both labeled and unlabeled data.
result Method learns fair and stable decision policies with high utility.
Classification from Positive and Biased Negative Data with Skewed Labeled Posterior Probabilitystat.ME
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.
We evaluate the folk wisdom that algorithmic decision rules trained on data produced by biased human decision-makers necessarily reflect this bias. We consider a setting where training labels are only generated if a biased decision-maker takes a particular action, and so "biased" training data arise due to discriminato…
Classification under Nuisance Parameters and Generalized Label Shift in Likelihood-Free Inferencestat.ML
New method corrects biased predictions and uncertainty estimates in classification with nuisance parameters.
problem Tackles biased predictions and invalid uncertainty estimates in classification with nuisance parameters.
method Proposes a method that estimates ROC across the entire nuisance parameter space to devise invariant cutoffs.
result Demonstrates effective domain adaptation and valid prediction sets with high power.
Algorithm improves binary classification of biased grouped data.
problem Improving binary classification for biased, grouped data.
method Assumes partition-projected class-conditional invariance across groups and derives a semi-supervised algorithm to learn a group-aware classifier.
result Demonstrates improved area under the ROC curve compared to baselines.
We present a unified invariance framework for supervised neural networks that can induce independence to nuisance factors of data without using any nuisance annotations, but can additionally use labeled information about biasing factors to force their removal from the latent embedding for making fair predictions. Invar…
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.
Study data biases to predict algorithmic discrimination, developing a Data Bias Profile.
problem Data biases contribute to algorithmic discrimination, but their impact is understudied.
method Analyzed three common data biases across various datasets and models, developing a Data Bias Profile.
result Combination of proxies and label bias can lead to more significant discrimination than underrepresentation alone.
Proposes a new method for handling domain shift in samples with biases in both covariates and labels.
problem Domain shift in samples with biases in both covariates and labels.
method Factorizable Joint Shift (FJS) and Joint Importance Aligning (JIA).
result Our method can handle co-existence of sampling bias in covariates and labels.
Learning disentangled representations is considered a cornerstone problem in representation learning. Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised methods do not allow to…
The paper tackles fairness in machine learning by modeling latent unbiased labels.
problem Ensuring fairness in machine learning systems that use biased data.
method Explicitly models a latent variable representing a hidden, unbiased label to achieve demographic parity.
result The latent variable approach successfully retrieves fair labels from biased data.
WeLa-VAE learns interpretable disentangled representations with weak supervision.
problem Learning disentangled representations without strong supervision.
method Variational inference framework with shared latent variables and modified variational lower bound.
result WeLa-VAE learns alternative disentangled representations (polar) from weak labels (distance and angle) without refined supervision.
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.
Paper tackles long-tailed labels in classification problems.
problem Imbalanced or long-tailed label distribution in real-world classification problems.
method Logit adjustment applied post-hoc or during training to encourage a large relative margin between rare and dominant labels.
result Unified and generalised techniques for coping with long-tailed labels, improving generalisation and performance.
Multiple fairness constraints have been proposed in the literature, motivated by a range of concerns about how demographic groups might be treated unfairly by machine learning classifiers. In this work we consider a different motivation; learning from biased training data. We posit several ways in which training data m…
New method uses imperfect LLM annotations for valid statistical inference in social science.
problem Inaccurate large language model annotations in social science research.
method Design-based supervised learning (DSL) combining imperfect LLM surrogates with gold-standard labels.
result DSL provides valid statistical inference with comparable predictive accuracy to existing methods.
We consider adversarial examples for image classification in the black-box decision-based setting. Here, an attacker cannot access confidence scores, but only the final label. Most attacks for this scenario are either unreliable or inefficient. Focusing on the latter, we show that a specific class of attacks, Boundary …
Develops methods to correct bias in AI feedback for more accurate alignment.
problem Systematic bias in AI feedback compared to human labels.
method Two debiased alignment methods: DDPO and DIPO.
result Methods improve alignment efficiency and performance close to human-labeled data.
Interpolating label noise makes models vulnerable to adversarial attacks.
problem Adversarial vulnerability of models trained on noisy labels.
method Theoretical analysis of label noise and adversarial risk relationship.
result Uniform label noise induces adversarial risk similar to worst-case poisoning.
Beyond the Selected Completely At Random Assumption for Learning from Positive and Unlabeled Datacs.LG
Most positive and unlabeled data is subject to selection biases. The labeled examples can, for example, be selected from the positive set because they are easier to obtain or more obviously positive. This paper investigates how learning can be ena BHbled in this setting. We propose and theoretically analyze an empirica…
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…
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%.
Method trains a debiased model from a biased one by focusing on samples that contradict the bias.
problem Training neural networks can lead to biased predictions due to spurious correlations.
method Train a pair of neural networks, intentionally biasing one and debiasing the other by focusing on contradictory samples.
result Our method significantly improves training against various types of biases, sometimes outperforming explicit supervision methods.
The paper studies how to use AI-generated labels in econometrics to avoid bias.
problem Small misclassification errors in AI-generated labels can lead to large biases in econometric estimators.
method The paper proposes a coupled-label bootstrap method to correct bias and deliver valid inference.
result The coupled-label bootstrap method is valid without the strong independence condition between true and imputed labels.
FreDF improves forecasting by learning in the frequency domain.
problem Label autocorrelation in future forecasts is often overlooked in time series modeling.
method FreDF learns to forecast in the frequency domain to mitigate label autocorrelation.
result FreDF significantly outperforms existing methods in forecasting accuracy.
In semi-supervised learning for classification, it is assumed that every ground truth class of data is present in the small labelled dataset. Many real-world sparsely-labelled datasets are plausibly not of this type. It could easily be the case that some classes of data are found only in the unlabelled dataset -- perha…
Metric evaluates symmetry-breaking in datasets, revealing severe biases.
problem Symmetry-breaking in datasets can hinder the performance of symmetry-aware methods.
method Developed a metric to quantify symmetry-breaking using a two-sample classifier test.
result Symmetry-breaking can prevent optimal performance of invariant methods, even when labels are invariant.
Improves SSL with doubly robust estimation of unlabeled class distribution.
problem Limited labeled data and long-tailed class distributions in unlabeled data.
method Explicitly estimate unlabeled class distribution using doubly robust estimator.
result Improves performance of SSL methods on unlabeled data.
Two strategies extend multi-label chaining for imprecise probability estimates.
problem Handling imprecise probability estimates in multi-label classification.
method Adapting multi-label chaining to use convex sets of distributions (credal sets).
result Adapted approaches produce relevant cautiousness on hard-to-predict instances.
Multi-instance learning (MIL) deals with tasks where data is represented by a set of bags and each bag is described by a set of instances. Unlike standard supervised learning, only the bag labels are observed whereas the label for each instance is not available to the learner. Previous MIL studies typically follow the …
Faced with distribution shift between training and test set, we wish to detect and quantify the shift, and to correct our classifiers without test set labels. Motivated by medical diagnosis, where diseases (targets) cause symptoms (observations), we focus on label shift, where the label marginal changes but the …
Study shows how online personalization can lead to unfair models due to biased user responses.
problem Fairness issues in online personalization systems due to biased user responses.
method Formulated a regularization-based approach to mitigate biases in machine learning models.
result Demonstrated that online personalization can cause models to learn unfair behavior from biased user responses.
Entity resolution (ER) presents unique challenges for evaluation methodology. While crowdsourcing platforms acquire ground truth, sound approaches to sampling must drive labelling efforts. In ER, extreme class imbalance between matching and non-matching records can lead to enormous labelling requirements when seeking s…
Algorithm identifies best arm with biased proxy and selective ground truth audits.
problem Fixed-confidence best-arm identification with biased proxy and selective ground truth.
method Propensity-weighted estimator and adaptive auditing algorithm.
result Plug-in Neyman rule achieves near-oracle audit efficiency.
Machine learning's data-centric philosophy conflicts with natural sciences' standards.
problem Conflict between machine learning's ontology and epistemology and natural sciences' practices.
method Identifying and analyzing contexts where ML can be beneficial or harmful in natural sciences.
result ML can enhance trustworthiness in causal inference but introduces biases in emulation and labeling.
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.
Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Datacs.LG
Deep RL detects anomalies from few labeled examples and large unlabeled data.
problem Anomaly detection with limited labeled data and large unlabeled data.
method Deep reinforcement learning to optimize detection of labeled and unlabeled anomalies.
result Significantly outperforms state-of-the-art methods on 48 real-world datasets.
A self-supervised debiasing method using rank regularization mitigates spurious correlations in neural networks.
problem Spurious correlations cause biases in deep neural networks, affecting generalization.
method Spectral analysis of latent representations, rank regularization, self-supervised pretraining, debiasing of downstream tasks.
result The proposed framework significantly improves generalization performance and outperforms supervised debiasing approaches.
PPAT uses predictions to improve risk estimation in active testing.
problem Exploiting informative predictions from black-box models for efficient risk estimation.
method Combines LURE estimator with prediction-powered control variate.
result PPAT outperforms existing methods in risk estimation and uncertainty quantification.
Deep learning from crowdsstat.ML
Over the last few years, deep learning has revolutionized the field of machine learning by dramatically improving the state-of-the-art in various domains. However, as the size of supervised artificial neural networks grows, typically so does the need for larger labeled datasets. Recently, crowdsourcing has established …
In the early history of positive-unlabeled (PU) learning, the sample selection approach, which heuristically selects negative (N) data from U data, was explored extensively. However, this approach was later dominated by the importance reweighting approach, which carefully treats all U data as N data. May there be a new…