| Active Embedding Search via Noisy Paired Comparisons | active learning |
| Batch Decorrelation for Active Metric Learning | active learning |
| BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning | active learning |
| Active Ordinal Querying for Tuplewise Similarity Learning | active learning |
| The Sample Complexity of Best-k Items Selection from Pairwise Comparisons | active learning |
| Fair Active Learning | active learning
bias and fairness |
| Crowd Teaching with Imperfect Labels | active learning
weak supervision |
| Asking the Right Questions to the Right Users: Active Learning with Imperfect Oracles | active learning
weak supervision |
| Generative Adversarial Active Learning for Unsupervised Outlier Detection | active learning
outlier & OoD detection |
| Semi-Supervised Sequence Modeling with Cross-View Training | semi-supervised |
| Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results | semi-supervised |
| Fixmatch: Simplifying semi-supervised learning with consistency and confidence | semi-supervised |
| Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning | semi-supervised |
| Semi-Supervised Learning With Scarce Annotations | semi-supervised |
| Benchmarking Semi-supervised Federated Learning | semi-supervised |
| VT FeatMatch: Feature-Based Augmentationfor Semi-Supervised Learning | semi-supervised
data augmentation |
| Unsupervised Data Augmentation for Consistency Training | semi-supervised
data augmentation |
| Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning | semi-supervised
adversarial training |
| Rethinking the Value of Labels for Improving Class-Imbalanced Learning | semi-supervised
class imbalance
self-supervision |
| VT Stochastic Generalized Adversarial Label Learning | weak supervision |
| VT Self-Paced Robust Learning for Leveraging Clean Labels in Noisy Data | weak supervision
robustness & generalization |
| Snorkel: Rapid Training Data Creation with Weak Supervision | weak supervision |
| Data Programming Using Continuous and Quality-Guided Labeling Functions | weak supervision |
| Meta Label Correction for Noisy Label Learning | weak supervision |
| Does label smoothing mitigate label noise? | weak supervision |
| Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages | weak supervision |
| Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning | weak supervision |
| Partial Label Learning with Batch Label Correction | weak supervision
data augmentation |
| VT Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs | self-supervision |
| Bootstrap Your Own LatentA New Approach to Self-Supervised Learning | self-supervision |
| Contrastive Multi-View Representation Learning on Graphs | self-supervision |
| Self-supervised Learning from a Multi-view Perspective | self-supervision |
| Self-Supervised Learning of Pretext-Invariant Representations | self-supervision |
| Supervised Contrastive Learning | self-supervision |
| Graph Contrastive Learning with Augmentations | self-supervision
data augmentation |
| Adversarial Self-Supervised Contrastive Learning | self-supervision
adversarial training |
| SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning | data augmentation
self-supervision |
| KeepAugment: A Simple Information-Preserving Data Augmentation Approach | data augmentation |
| AutoAugment: Learning Augmentation Policies from Data | data augmentation |
| CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features | data augmentation |
| Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks | data augmentation |
| Implicit Semantic Data Augmentation for Deep Networks | data augmentation |
| Adversarial Training for Free! | adversarial training |
| Smooth Adversarial Training | adversarial training |
| Transferable Adversarial Training:A General Approach to Adapting Deep Classifiers | adversarial training |
| Adversarial Training and Provable Defenses: Bridging the Gap | adversarial training |
| Distributionally Adversarial Attack | adversarial training |
| Adversarial Policies: Attacking Deep Reinforcement Learning | adversarial training |
| Disentangling Adversarial Robustness and Generalization | adversarial training
robustness & generalization |
| On the Connection Between Adversarial Robustness and Saliency Map Interpretability | adversarial training interpretability
robustness & generalization |
| Structured Adversarial Attack: Towards General Implementation and Better Interpretability | adversarial training interpretability |
| VT Interpretable Event Detection and Extraction using Multi-Aspect Attention | interpretability |
| A Benchmark for Interpretability Methods in DeepNeural Networks | interpretability |
| Causal Interpretability for Machine Learning - Problems, Methods and Evaluation | interpretability |
| Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization | interpretability |
| ProtoAttend: Attention-Based Prototypical Learning | interpretability |
| Robustness in Machine Learning Explanations: Does It Matter? | interpretability
robustness & generalization |
| Measuring Robustness to Natural Distribution Shifts in Image Classification | robustness & generalization |
| Domain Generalization using Causal Matching | robustness & generalization |
| Coping with Label Shift via Distributionally Robust Optimisation | robustness & generalization |
| Self-Challenging Improves Cross-Domain Generalization | robustness & generalization |
| Multi-Object Representation Learning with Iterative Variational Inference | robustness & generalization |
| Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization | robustness & generalization |
| Faking Fairness via Stealthily Biased Sampling | bias and fairness |
| Robust Optimization for Fairnesswith Noisy Protected Groups | bias and fairness |
| Socially Responsible AI Algorithms:Issues, Purposes, and Challenges | bias and fairness |
| Neutralizing Self-Selection Bias inSampling for Sortition | bias and fairness |
| Learning from Positive and Unlabeled Data with a Selection Bias | bias and fairness |
| Counterfactual Fairness | bias and fairness |
| Equality of Opportunity in Supervised Learning | bias and fairness |
| Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings | bias and fairness |
| Language (Technology) is Power: A Critical Survey of “Bias” in NLP | bias and fairness |
| Verifying Individual Fairness in Machine Learning Models | bias and fairness |
| Biased Games | bias and fairness |
| Class-Balanced Loss Based on Effective Number of Samples | class imbalance |
| Dice Loss for Data-imbalanced NLP Tasks | class imbalance |
| ADASYN: Adaptive synthetic sampling approach for imbalanced learning | class imbalance |
| Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss | class imbalance |
| Striking the Right Balance with Uncertainty | class imbalance |
| Distribution-Balanced Loss for Multi-LabelClassification in Long-Tailed Datasets | class imbalance |
| Learning to Segment the Tail | class imbalance |
| M2m: Imbalanced Classification via Major-to-minor Translation | class imbalance |
| VT Multidimensional Uncertainty-Aware Evidential Neural Networks | outlier & OoD detection |
| Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks | outlier & OoD detection |
| SUOD: Toward Scalable Unsupervised Outlier Detection | outlier & OoD detection |
| Deep Sets | outlier & OoD detection |
| Automating Outlier Detection via Meta-Learning | outlier & OoD detection |
| Deep anomaly detection with outlier exposure | outlier & OoD detection |
| Further Analysis of Outlier Detection with Deep Generative Models | outlier & OoD detection |
| Energy-based Out-of-distribution Detection | outlier & OoD detection |
| Outlier Exposure with Confidence Control for Out-of-Distribution Detection | outlier & OoD detection |
| Explainable Deep One-Class Classification | outlier & OoD detection interpretability |
| Semi-Supervised Learning under Class Distribution Mismatch | outlier & OoD detection interpretability |
| Unsupervised Data Imputation via Variational Inference of Deep Subspaces | missing values/attributes |
| Missing Data Imputation using Optimal Transport | missing values/attributes |
| Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections | missing values/attributes |
| Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks | missing values/attributes |
| Multivariate Time Series Imputation with Generative Adversarial Networks | missing values/attributes |
| MCFlow: Monte Carlo Flow Models for Data Imputation | missing values/attributes |
| Learning on Attribute-Missing Graphs | missing values/attributes |
| Handling Missing Data with Graph Representation Learning | missing values/attributes |
| Inductive Matrix Completion Based on Graph Neural Networks | missing values/attributes |
