GANs learn from incomplete data with missing data imputation.
problem Learning from incomplete data with GANs.
method Proposes a GAN framework with a complete data generator and a mask generator to model missing data.
result Demonstrates effective imputation of missing data using adversarial training.
A new imputation method MissARF uses adversarial random forests for fast and accurate missing value imputation.
problem Handling missing values in biostatistical analyses.
method Adversarial Random Forests (ARF) for density estimation and data synthesis.
result MissARF performs comparably to state-of-the-art methods in imputation quality and runtime.
IFGAN uses feature-specific GANs for missing value imputation.
problem Missing value imputation in data mining.
method Feature-specific Generative Adversarial Networks (GAN).
result IFGAN outperforms state-of-the-art algorithms in various missing conditions.
Study linear regression with missing or corrupted data, showing error bounds.
problem Linear regression under missing or corrupted data.
method Information-theoretic lower bounds and efficient algorithms.
result Error bounds match in missing and corruption settings.
Paper proposes a framework for disease prediction from EHRs with missing data.
problem Missing data in EHRs for disease prediction.
method Two-stage framework including missing data imputation and disease prediction using GANs and stacked autoencoders.
result Significantly improved disease prediction accuracy with AC-GAN and stacked autoencoder.
GAIN uses GANs to impute missing data by forcing the generator to learn the true distribution.
problem Missing data in datasets.
method Adapting GAN framework to impute missing data, using a generator and discriminator.
result GAIN significantly outperforms state-of-the-art imputation methods on various datasets.
GANs improve missing data imputation for ranking tasks.
problem Missing data in ranking datasets violates standard assumptions.
method Conditional Imputation GAN for Extended Missing At Random and Extended Always Missing At Random mechanisms.
result Optimal GAN imputation for EMAR and EAMAR mechanisms.
PC-GAIN improves GAIN's imputation by incorporating category information.
problem Missing data in incomplete datasets.
method Pre-training with pseudo-labels and incorporating an auxiliary classifier into GAIN.
result Significantly improved imputation quality compared to GAIN.
HexaGAN tackles real-world classification issues with missing data, class imbalance, and missing labels.
problem Missing data, class imbalance, and missing labels in real-world data.
method Generative adversarial network framework with six components and novel loss functions.
result Up to 5% improvement in classification performance compared to state-of-the-art methods.
Proposes VIGAN for imputing missing views in multi-view datasets.
problem Missing view problem in multi-view datasets.
method Generative Adversarial Networks (GANs) and Multi-modal Denoising Autoencoder (DAE).
result VIGAN effectively recovers missing views from paired data across views.
Paper develops adaptive models for robust energy forecasting with missing data.
problem Operational models assume complete data; missing data can degrade forecast accuracy.
method Adaptive robust optimization and adversarial machine learning for missing data.
result Proposed models perform well even with short-term missing data and significantly outperform imputation with longer-term missing data.
Paper tackles policy optimization from observational data, overcoming missing counterfactuals and selection bias.
problem Optimizing policies from observational data in the absence of controlled experiments.
method Theoretical bounds on estimation errors of counterfactuals, domain adversarial neural networks.
result Effective domain adversarial training for choosing optimal policies.
Proposes a GNN-based method for robust missing data imputation.
problem Missing data imputation in scientific datasets.
method Graph denoising autoencoder with adversarially-trained GNNs.
result Robustly outperforms state-of-the-art approaches for MDI.
LGnet jointly models local and global dynamics for MTS forecasting with missing values.
problem Missing values in multivariate time series data.
method LGnet framework using memory network and adversarial training.
result LGnet effectively forecasts MTS with missing values and robust under various missing ratios.
Paper proposes WGAIN for missing feature reconstruction.
problem Missing data in datasets.
method Wasserstein Generative Adversarial Imputation Network (WGAIN) compared to traditional methods.
result WGAIN outperforms traditional methods in imputing missing data.
SARGAN uses GANs to fill in missing radar frequency bands.
problem Missing spectral information in low frequency radar bands.
method Generative adversarial network (GAN) trained on paired original and missing band signals.
result Initial results show promise in recovering missing spectral information.
CollaGAN uses GANs to impute missing image data.
problem Missing data bias in applications requiring multiple inputs.
method Collaborative Generative Adversarial Network (CollaGAN) for multi-domain image imputation.
result CollaGAN produces higher quality imputed images than existing methods.
Paper tackles missing data in irregularly-sampled time series.
problem Modeling irregularly-sampled time series data.
method Encoder-decoder framework based on variational autoencoders and generative adversarial networks.
result Models achieve competitive or better classification results on irregularly-sampled multivariate time series.
New method resolves bias in recommender learning without needing missing data.
problem Bias in offline recommender learning from explicit ratings.
method Proposes a novel algorithm to minimize generalization error bound via adversarial learning, independent of propensity estimation.
result Demonstrates superior performance in rating prediction and ranking metrics without missing completely at random data.
IVE-GAN improves GANs by mapping data to latent space, covering all modes.
problem GANs struggle to learn all modes of the true data generation process.
method IVE-GAN introduces an inverse mapping from data to latent space using invariant features.
result IVE-GAN generates rich representations and covers all modes of the data.
BlockEcho method improves imputation of block-wise missing data.
problem Block-wise missing data reduces interpolation capability and predictive power.
method Integrates Matrix Factorization (MF) within Generative Adversarial Networks (GAN) to retain long-distance inter-element relationships.
result Superior performance on public datasets across three domains, especially at higher missing rates.
Unified framework for multi-domain learning and data imputation.
problem Improving performance across different domains with missing data.
method Adversarial autoencoder for domain-invariant embeddings and data imputation.
result Superior performance compared to state-of-the-art methods in various settings.
Bi-GAN model for imputing and predicting irregular time-series data.
problem Irregularly observed, varying length time-series data with missing entries.
method Bi-GAN model using a bidirectional recurrent network in a generative adversarial setting.
result Bi-GAN model can impute and predict missing values for time-series of varying length.
New algorithm improves GAN performance with minimal labels.
problem Improving GAN performance with little supervision.
method Intentionally corrupts generated labels to match real data statistics, trains discriminator with corrupted labels.
result Minimizing proposed loss is equivalent to minimizing true divergence between real and generated data.
This study compares and improves deep generative models for missing data imputation.
problem Missing data in datasets can negatively impact machine learning models.
method Comparison and improvement of deep generative models (GANs and VAEs) for missing data imputation.
result The presence or absence of categorical variables affects the selection of the best model, and some models are more stable than others.
Infer-AVAE infers missing user attributes from incomplete data using a novel adversarial approach.
problem Incomplete user attributes in social networks.
method Infer-AVAE combines MLP and GNNs with adversarial training to infer missing attributes.
result Infer-AVAE outperforms baselines by 7.0% in accuracy on real-world datasets.
Adversarial quantum-classical model learns and infers data faster.
problem Training quantum circuits is harder than classical neural networks.
method Coupling quantum generator with classical discriminator for training.
result Quantum circuit can infer missing data with quadratic speed up.
MMD test detects adversarial attacks by addressing kernel limitations and non-independence issues.
problem MMD test's failure to detect adversarial attacks.
method Replaced Gaussian kernel with deep kernel, maximized test power, and used wild bootstrap for non-independence.
result MMD test is aware of adversarial attacks.
A novel GAN approach for multiview learning with missing data.
problem Learning from multiview data with missing observations.
method Biconditional GAN with two generators and a discriminator for conditional generation of missing views.
result The discriminator achieves significant classification performance and generators learn missing views without external resources.
A GAN variant synthesizes missing MRI sequences from available ones.
problem Missing MRI sequences due to various constraints.
method Multi-modal Generative Adversarial Network (GAN) that combines multiple available sequences to synthesize missing ones.
result The proposed GAN method outperforms competing approaches in synthesizing missing MRI sequences.
Algorithm completes symmetric tensors from few entries, learns product mixtures.
problem Learning product mixtures over the hypercube from incomplete data.
method Tensor completion algorithm applied to matrix completion for adversarially missing entries.
result Recover distributions with many centers in polynomial/quasi-polynomial time.
Deep learning models outperform MICE in large survey imputation but with hyperparameter tuning.
problem Comparing deep learning and MICE for missing data imputation in large surveys.
method Extensive simulation studies comparing four machine learning-based MI methods: MICE with classification trees, MICE with random forests, generative adversarial imputation networks, and multiple imputation using denoising autoencoders.
result MICE with classification trees consistently outperforms deep learning methods in terms of bias, mean squared error, and coverage.
Study on estimating Gaussian mean with missing data in high dimensions.
problem Estimating Gaussian mean in high dimensions with missing data due to realizable contamination.
method Statistical Query model, Low-Degree Polynomials, PTF tests, and algorithms.
result Established information-computation gap and developed efficient algorithms.
GANs improve longitudinal data imputation but face challenges in missing data and class imbalance.
problem Missing data and class imbalance in longitudinal data.
method GANs applied to longitudinal data imputation (LDI).
result GANs show potential but need more versatile approaches.
AdaGAN uses boosting to improve GANs by iteratively adding components.
problem GANs struggle with missing modes in complex data.
method AdaGAN is an iterative procedure that adds new components to a mixture model using a GAN algorithm on reweighted samples, inspired by boosting.
result AdaGAN addresses the problem of missing modes in GANs.
New GAN model deblends galaxy images with high accuracy and speed.
problem Deblending blended galaxy images in dense regions of the universe.
method Branched generative adversarial network (GAN) to produce images of deblended galaxies.
result High peak signal-to-noise ratio and structural similarity scores compared to ground truth images.
Generates missing node attributes for better graph-based tasks.
problem Missing or incomplete node attributes degrade graph-based algorithms' performance.
method Deep adversarial learning-based method (NANG) to generate node attributes.
result Generated node attributes improve node classification and link prediction.
Generative Adversarial Networks create synthetic PNRs for airline industry.
problem Creating realistic synthetic Passenger Name Records without infringing data ownership laws.
method Cramér GANs, categorical feature embedding, Cross-Net architecture.
result Generated PNRs match real data well and can be used for business applications.
Zero imputation leads to suboptimal neural network performance.
problem Suboptimal performance in neural networks due to missing data.
method Introduced Sparsity Normalization (SN) to handle missingness.
result Debiasing input-level sparsity improves neural network performance and stability.
This paper proposes a new method to improve adversarial robustness of DNNs by focusing on semantic information.
problem Vulnerability of deep neural networks to adversarial attacks.
method Region adversarial training (RAT) that generates a single adversarial perturbation carrying semantic information.
result RAT greatly improves adversarial robustness with a small dataset and defends against FGSM attacks.
IGANI uses iterative GANs to improve traffic data imputation.
problem Imputation of traffic data in the absence of sensor data.
method Iterative Generative Adversarial Networks (IGANI) for unsupervised learning.
result IGANI produces more accurate imputation results compared to previous methods.
NAOMI improves imputation accuracy for long-range sequences.
problem Missing value imputation in spatiotemporal data.
method Non-autoregressive deep generative model exploiting multiresolution structure.
result Significant improvement in imputation accuracy (60% reduction in average prediction error).
The paper compares methods for imputing missing categorical data in supervised classification tasks.
problem Missing data in categorical variables can degrade model performance.
method Experimented on two datasets with missing categorical data, comparing imputation methods with and without additional missing-data perturbation.
result Imputation methods can increase predictive accuracy in the presence of missing-data perturbation.
Adversarial method finds rare catastrophic failures in safety-critical agents.
problem Evaluating safety-critical learning systems for catastrophic failures.
method Adversarial evaluation approach focusing on rare adversarial situations.
result Adversarial evaluation finds catastrophic failures and estimates failure rates faster.
Study on missing data mechanisms and simple imputation methods in fairness of machine learning algorithms.
problem Impact of missing data mechanisms and simple imputation methods on fairness of machine learning algorithms.
method Three popular datasets for classification fairness were used. Missing values were generated using three missing data mechanisms. Various missing data handling techniques (listwise deletion, mean imputation, mode imputation, multiple imputation) were applied to the datasets. Fairness was assessed using classification algorithms (random forests).
result Missing data mechanism does not significantly impact fairness; listwise deletion gives highest fairness on average.
A new method uses denoising diffusion models to improve seismic data interpolation.
problem Improving the accuracy of seismic data interpolation to enhance imaging and interpretation.
method The approach combines denoising diffusion probabilistic models with coherence-corrected resampling strategies.
result The proposed method achieves superior performance and generalization to various missing patterns and noise levels.
Paper shows adversarial attacks are possible in real-time video classification systems.
problem Adversarial perturbations in real-time video classification systems.
method Exploits GAN architectures to generate stealthy adversarial samples.
result Generative adversarial networks can cause misclassification rates of over 80% in real-time video classification.
Our work proves convergence to low robust training loss for polynomial width ReLU networks.
problem Understanding why adversarial training leads to low robust training loss in over-parameterized neural nets.
method Extending convergence theory for standard supervised training to adversarial training, using tools from online learning and showing ReLU networks can approximate the step function.
result Convergence to low robust training loss for polynomial width ReLU networks under natural assumptions.