New methods improve deep learning on imbalanced datasets.
problem Poor performance of deep learning on imbalanced datasets.
method Label-distribution-aware margin (LDAM) loss and a training schedule.
result Combination of methods achieves significant performance gains.
Max-pooling improves semantic segmentation by re-weighting under-represented classes.
problem Imbalanced training data distributions in semantic image segmentation datasets.
method Adaptive loss max-pooling that re-weights pixel contributions based on observed losses.
result Consistently improved semantic segmentation results on benchmark datasets.
Generative Adversarial Network model for class-imbalanced tabular data.
problem Class imbalance in binary classification problems.
method Generative Adversarial Network (GAN) with synthetic minority class samples.
result Improves average precision compared to re-weighting and oversampling techniques.
The paper analyzes how re-weighting helps in reducing variance in high-dimensional kernel methods under covariate shifts.
problem The challenge of high-dimensional kernel methods under covariate shifts and the role of re-weighting.
method Derives asymptotic expansion of high-dimensional kernels under covariate shifts, analyzes bias-variance decomposition, and characterizes the regularized kernel.
result Re-weighting helps in decreasing variance and can be seen as a data-dependent regularization.
PARIS reduces imbalanced regression datasets by pruning uninformative samples.
problem Imbalanced regression where models focus on high-frequency regions, ignoring rare but impactful events.
method PARIS uses the representer theorem to compute a closed-form representer deletion residual for iterative pruning of the training set.
result PARIS reduces training set by up to 75% while preserving or improving overall performance, outperforming other methods.
Optimizes CNNs by directing gradients along output channels.
problem Improving generalization error in CNNs.
method Output-channel directed re-weighted L2 or Sobolev metrics.
result Improves generalization error by optimizing gradients.
A new method generates counterfactual treatment outcomes for time-varying treatments.
problem Estimating counterfactual outcomes for time-varying treatments with high-dimensional outcomes.
method Conditional generative framework with inverse probability re-weighting.
result Our method outperforms state-of-the-art baselines in generating high-quality counterfactual samples.
New method enhances adversarial robustness of deep learning models.
problem Improving the robustness of deep learning models against adversarial attacks.
method Optimal transport regularized divergences applied to distributionally robust optimization.
result Improved adversarial robustness on CIFAR-10 and CIFAR-100 datasets.
Corrects bias in machine learning models by re-weighting data points.
problem Machine learning models inherit biases from training data.
method Formulates bias mathematically, corrects it by re-weighting data points.
result Training on re-weighted data yields an unbiased classifier.
Investigates upsampling vs. upweighting for balanced training on skewed datasets.
problem Balancing training on heavily imbalanced datasets with scarce data.
method Theoretical and empirical analysis of upsampling and upweighting strategies.
result Upsampling and upweighting diverge under stochastic gradient descent, with upsampling leading to faster convergence but higher overfitting risk.
A new algorithm improves SVM models by making them sparser and more stable.
problem Training SVM models with sparsity and stability.
method Modified Frank-Wolfe algorithm with re-weighted L2 SVM.
result The algorithm produces sparser SVM models with improved stability.
Solves complex machine learning problems with IRW method.
problem Problems with intractable sparsity-inducing norms in machine learning.
method Iteratively Re-Weighted (IRW) method with convergence guarantee.
result IRW method significantly outperforms alternative methods in robust feature selection.
Improved cGANs using GOLD measure for better data distribution alignment.
problem Improving the quality and controllability of cGANs.
method Measuring the discrepancy between data and model distributions using GOLD.
result Proposed GOLD measure improves cGANs in training, inference, and data selection.
M2m method improves deep learning performance on class-imbalanced datasets.
problem Class imbalance in labeled training datasets causes deep neural networks to generalize poorly to minority classes.
method Augment less-frequent classes by translating samples from more-frequent classes.
result Significantly improves generalization on minority classes compared to existing methods.
New method makes CP intervals locally adaptive using trainable transformations.
problem Making Conformal Prediction intervals locally adaptive.
method Defining a trainable change of variables φ X ( A ) φ_X(A) φ X ( A ) that depends on object attributes X X X . result Locally adaptive prediction intervals with guaranteed marginal validity and variable sizes.
A new method uses modified Boltzmann weights to infer system configurations from observed data.
problem Inference of system configurations from limited observed data.
method Data-driven approach based on re-weighting observed configurations to achieve a flat distribution probability.
result Accurate inference of system configurations with high-temperature re-weighting of observations.
DisCor corrects reinforcement learning issues by re-weighting collected data.
problem Reinforcement learning algorithms struggle with instability and sensitivity to hyperparameters.
method DisCor reweights collected data to mitigate issues caused by the distribution of experience.
result DisCor improves reinforcement learning in challenging settings like multi-task learning and noisy reward signals.
Estimates causal contributions of multiple causes on outcome changes.
problem Quantifying the effect of multiple causes on an outcome change.
method Develops a multiply robust estimation strategy combining regression and re-weighting methods.
result The method recovers the target parameter under partial misspecification and is consistent and asymptotically normal.
Develops a novel ANN model to remove bias in machine learning predictions.
problem Bias in machine learning predictions due to data used for subsequent model training.
method Adversarial Neural Network (ANN) model to create bias-invariant data representation.
result Empirically successful on synthetic and real-world data.
Gradient-free SVGD improves inference for complex distributions.
problem Applying SVGD when gradients are unavailable.
method GF-SVGD, using a surrogate gradient and re-weighting.
result GF-SVGD outperforms gradient-free MCMC methods.
Innovative game theory approach optimizes survival analysis metrics.
problem Survival analysis models trained with maximum likelihood do not directly optimize criteria like Brier score or Bernoulli log likelihood.
method Inverse-Weighted Survival Games: Construct objectives from re-weighted estimates featuring the other model, holding the latter fixed during training.
result Games optimize Brier score on simulations and real-world data.
A new method aligns source and target distributions by tuning their weights.
problem Domain adaptation on unlabeled target datasets using labeled source datasets.
method Weighted Joint Distribution Optimal Transport (WJDOT) method that finds alignment between source and target distributions and re-weighting of source distributions.
result Achieves state-of-the-art performance on simulated and real-life datasets.
Sparse R-LSSVM improves robustness and sparsity of LSSVM.
problem Robustness and sparsity issues in LSSVM.
method Interpreting robustness as a re-weighted problem, proposing a sparse R-LSSVM algorithm using low-rank approximation and entropy penalty.
result Proposed SR-LSSVM achieves sparse solutions efficiently for large-scale problems.
A new method for high-dimensional classification using Bernstein polynomials.
problem Computational difficulties in high-dimensional SVM hinge loss.
method Proposes Bernstein support vector machine (BernSVM) and two efficient algorithms.
result Achieves a prediction accuracy rate of s log ( p ) / n \sqrt{s\log(p)/n} s log ( p ) / n with high probability. New method improves model generalization across different designs without strong assumptions.
problem Improving model generalization under distributional shift in causal inference and unsupervised domain adaptation.
method Develops a bound on generalization error under design shift, incorporating representation learning and sample re-weighting, without requiring well-specified models or pre-specified metrics.
result Empirically validated framework outperforms previous methods in synthetic datasets.
Estimates calibration error under label shift without labels.
problem Ensuring model reliability in the face of dataset shift without access to labels.
method Importance re-weighting of the labeled source distribution to estimate calibration error under label shift.
result Effective and reliable CE estimation with respect to the shifted target distribution.
This paper compares unsupervised domain adaptation methods for vision tasks.
problem Limited labeled data across domains leads to poor model performance.
method Classifies and compares non-deep and deep unsupervised domain adaptation methods.
result Summarizes and discusses potential directions for unsupervised domain adaptation.
Study shows pre-trained models can handle long-tailed relations well, improving classifier performance.
problem Challenges in long-tailed relation classification due to class imbalance.
method Used instance-balanced sampling to pre-train models and then improved classifier performance through attentive relation routing.
result Robust classifier with attentive relation routing achieves better long-tailed classification ability.
OPERA blends multiple OPE estimators to evaluate new policies offline.
problem Lack of reliable offline policy evaluation methods for new policies.
method Adaptive blending of multiple OPE estimators without explicit selection.
result Consistent and reliable policy evaluation framework for offline RL.
A new approach to learn weights for multi-view clustering.
problem Measuring the importance of each view in multi-view clustering.
method Proposes a re-weighted approach to learn intrinsic weights for multi-view clustering.
result The proposed approach is effective and practical for multi-view clustering.
URT layer improves few-shot image classification across diverse domains.
problem Few-shot image classification in multi-domain settings.
method Meta-learns to dynamically re-weight and compose domain-specific representations.
result Sets new state-of-the-art on Meta-Dataset.
CSGE combines multiple models for better machine learning performance.
problem Creating models that generalize well for complex datasets.
method Coopetitive Soft Gating Ensemble (CSGE) for machine learning and autonomic computing.
result CSGE achieves state-of-the-art performance for classification and regression tasks.
New approach tackles domain adaptation without assuming domain invariant representations.
problem Learning models on source domains for target domains with labeled and unlabeled data.
method Hidden Covariate Shift hypothesis; learning representation to match joint distributions.
result State-of-the-art performance on Amazon Reviews dataset.
Improved DeepONets for PDE solution operators with adaptive re-weighting and new architecture.
problem Training DeepONets for PDE solution operators without paired data.
method Adaptive re-weighting of training examples and novel network architecture.
result Consistently improved predictive accuracy by a factor of 10-50x.
A new kernel improves tensor classification accuracy and reduces computation time.
problem Challenges in classifying high-dimensional tensor data.
method Proposes a weighted subspace exponential kernel based on Tucker decomposition.
result The new kernel outperforms existing methods in accuracy and computational efficiency.
Improves neural network performance by dynamically adjusting model weights based on source reliability.
problem Training neural networks on data from unreliable sources leads to poor performance.
method Dynamic re-weighting strategy using likelihood tempering to adjust model weights based on estimated source reliability.
result Significant improvement in model performance when trained on mixtures of reliable and unreliable data sources.
The paper discusses selecting predictive models for causal inference, highlighting the challenges and proposing a solution.
problem Selecting the best predictive models for causal inference from a variety of machine learning models.
method The paper proposes using R e x t − r i s k R ext{-risk} R e x t − r i s k , flexible estimators, and splitting data to compute risks for model selection. result The proposed method controls both outcome errors for treated and non-treated individuals, addressing the issue of model selection for causal inference.
We propose a minimum distance estimation method for robust regression in sparse high-dimensional settings. The traditional likelihood-based estimators lack resilience against outliers, a critical issue when dealing with high-dimensional noisy data. Our method, Minimum Distance Lasso (MD-Lasso), combines minimum distanc…
A new framework SIMBA improves graph classification performance on size-imbalanced datasets.
problem Size imbalance in graph classification leads to poor model performance.
method Energy-guided structural smoothing between head and tail graphs, re-weighting based on energy propagation.
result SIMBA outperforms existing methods in size-imbalanced graph classification tasks.
Self-supervised learning performs better than supervised learning on imbalanced datasets.
problem The performance gap between balanced and imbalanced pre-training with self-supervised learning is smaller than with supervised learning.
method Systematic investigation of self-supervised learning under dataset imbalance, including experiments and theoretical analyses.
result Self-supervised representations are more robust to class imbalance than supervised representations.
Compress U-net by over 1000x with knowledge distillation.
problem Compressing U-net architecture while maintaining performance.
method Knowledge distillation with regularization methods.
result Compressed U-net by 1000x with negligible performance drop.
One-step Bellman alignment improves online RL by reducing task mismatch.
problem Online RL struggles with task similarity defined by rewards or transitions.
method One-step Bellman alignment and re-weighted targeting (RWT) to correct task mismatch.
result Regret bounds show task shift complexity, not target MDP, affects performance.
A method to improve time series forecasting by dynamically adjusting weights of forecasters.
problem Challenges in time series forecasting due to evolving data distributions.
method Dynamic re-weighting of forecasters based on evolving data distributions.
result Competitive performance compared to state-of-the-art methods for combining forecasters.
FAIR method uses adversarial training to learn fair instance weights.
problem Reduces bias in machine learning predictions through fair instance weighting.
method Adversarial training to learn instance weighting function ensuring fair predictions.
result Demonstrates better trade-off between accuracy and fairness compared to other models.
Improved acoustic modeling with attentive adversarial learning.
problem Domain variability in acoustic modeling.
method Proposes an attentive ADIT method with an attention mechanism to improve domain-invariance of deep features.
result Improves deep feature domain-invariance and senone-discriminativity over ADIT.
This paper improves image retrieval accuracy through novel relevance feedback methods.
problem Improving image retrieval accuracy in Content-Based Image Retrieval (CBIR).
method Novel addition to feature re-weighting and classification techniques, focusing on 0-th iteration improvement.
result Significantly improved retrieval accuracy from relevance feedback.
Paper proposes a new meta-learning approach for correcting noisy labels.
problem Learning with noisy labels in machine learning models.
method Meta-learned instance re-weighting approach extended to label correction problem.
result Proposed MLC (Meta Label Correction) framework achieves large improvements over previous methods.
In real-world classification problems, the class balance in the training dataset does not necessarily reflect that of the test dataset, which can cause significant estimation bias. If the class ratio of the test dataset is known, instance re-weighting or resampling allows systematical bias correction. However, learning…