Paper introduces a real-world image dataset for federated learning.
problem Lack of high-quality real-world data for federated learning.
method Created a dataset from 26 street cameras and 7 categories, implemented YOLO and Faster R-CNN.
result Benchmarked model performance, efficiency, and communication in federated learning.
Study finds real-world datasets contain natural experiments that can improve model performance.
problem Detecting natural experiments in real-world datasets for causal inference.
method Synthetic graph simulation and feature selection based on causal links.
result Real-world datasets contain natural experiments that can be exploited for improved model performance.
Study real-world noisy labels from human annotations for better understanding.
problem Understanding and modeling real-world label noise in machine learning.
method Developed two new benchmark datasets (CIFAR-10N, CIFAR-100N) with human-annotated real-world noisy labels.
result Real-world noisy labels exhibit instance-dependent patterns, not class-dependent as previously assumed.
Study introduces a benchmark suite for evaluating neural MI estimators on real-world unstructured datasets.
problem Lack of comprehensive evaluation methods for neural MI estimators on real-world unstructured datasets.
method Developed a benchmark suite using same-class sampling and a binary symmetric channel trick.
result Showed accurate manipulation of true MI values of real-world datasets.
Improved tabular models learn better from real-world data.
problem Tabular models perform poorly on real-world datasets when trained only on synthetic data.
method Continued pre-training on a curated set of real-world datasets.
result Real-TabPFN achieves superior predictive accuracy on 29 datasets.
Paper addresses challenges in benchmarking stream learning algorithms with real-world data.
problem Lack of publicly available non-stationary real-world datasets for evaluating stream algorithms.
method Proposes a new public data repository for benchmarking stream algorithms with real-world data.
result Mitigates problems related to dataset choice in experimental evaluation of stream classifiers and drift detectors.
A new method, InfoGuide, improves automatic clustering analysis.
problem Lack of automatic clustering analysis frameworks.
method Capturing traces of information gain between clustering retrievals.
result InfoGuide can enable more automatic clustering analysis.
Study evaluates scalability and real-world impact of disentangled representations.
problem Scalability and real-world impact of disentangled representations.
method New high-resolution dataset and architectures for disentangled representation learning.
result Disentanglement predicts out-of-distribution task performance.
This paper analyzes and improves active learning techniques for real-world projects.
problem Reducing labelling effort in machine learning models with real-world constraints.
method Systematic study of active learning issues, proposing techniques to address model convergence, annotation error, and dataset imbalance.
result Presentation of two techniques to speed up active learning: partial uncertainty sampling and larger query size.
Paper presents new dataset for disentanglement learning from physical objects.
problem Transfer of disentanglement models from synthetic to real-world data.
method Developed a dataset of physical objects with controlled variations, used a robotic arm for precise manipulation.
result Disentanglement models perform poorly on real data but selection of models and hyperparameters improves transfer.
Study reveals how spectral bias affects learnability on real-world data.
problem Understanding how well complex datasets can be learned using kernel methods.
method Use eigenvalues and eigenfunctions from idealized data to reveal spectral bias on real-world data.
result Bound learnability on real-world data using symmetries of realistic kernels.
New model detects crying in real-world settings with improved accuracy.
problem Generalization of cry detection models to real-world environments.
method Evaluated machine learning approaches on a novel dataset of real-world infant crying.
result Improved F1 score of 0.613 for crying event recognition in real-world settings.
We uncover scaling laws and statistical structure in complex datasets.
problem Understanding universal traits in complex datasets.
method Analogizing data to physical systems, using statistical physics and RMT.
result Real-world datasets and Gaussian data with long-range correlations share the same RMT universality class.
This paper benchmarks active learning methods for logistic regression and finds uncertainty sampling performs well.
problem Benchmarking and comparing active learning methods for logistic regression.
method State-of-the-art active learning methods for logistic regression were benchmarked and compared.
result Uncertainty sampling performs exceptionally well overall.
HNHN learns from hypergraphs with hyperedge neurons for better classification.
problem Learning from hypergraphs with complex relationships.
method Hypergraph convolution network with hyperedge neurons and adaptive normalization.
result Improved classification accuracy and speed compared to state-of-the-art methods.
SurvHTE-Bench benchmarks HTE estimation in survival analysis with diverse datasets.
problem Challenges in estimating HTEs from right-censored survival data.
method Modular synthetic datasets, semi-synthetic datasets, and real-world datasets.
result First rigorous comparison of survival HTE methods under diverse conditions.
We created financial benchmarks for distribution shifts in crude oil prices and volatility.
problem Scarcity of task-labeled time-series benchmarks in finance.
method Transformed asset price data into volatility proxies, generated task labels based on distribution shifts, and made datasets publicly available.
result Inclusion of task labels improves continual learning algorithms' performance on real-world data.
XAI-Bench releases synthetic datasets for evaluating feature attribution methods.
problem Evaluating and comparing feature attribution methods is challenging.
method Released synthetic datasets and benchmarking library.
result Efficiently evaluates feature attribution methods across various metrics.
New algorithms improve federated learning accuracy and stability with real-world data.
problem Real-world data diversity and imbalance challenge federated learning.
method Developed new algorithms (FedVC, FedIR) to resample and reweight data.
result Significant improvements in accuracy and stability of federated learning.
Modern CATE models often fail to outperform a trivial zero-effect predictor, highlighting significant challenges.
problem Lack of robustness in CATE models when applied to real-world data.
method Large-scale benchmark study using diverse observational sampling strategies and novel statistics.
result 62% of CATE estimates have higher MSE than a trivial zero-effect predictor, indicating poor performance.
Framework for applying GPs to real-world data with scalability guidelines.
problem Deployment of Gaussian Processes (GPs) is hindered by computational costs and lack of guidelines.
method Proposed a framework for identifying GP suitability and setting up robust models, formalizing decisions of experienced practitioners.
result More accurate results at test time for glacier elevation change case study.
VIRTUAL improves federated multi-task learning for non-convex models.
problem Real-world federated datasets show statistical heterogeneity.
method VIRTUAL treats federated network as a star-shaped Bayesian network and uses variational inference.
result VIRTUAL outperforms state-of-the-art for federated learning on real-world datasets.
PNNs improve treatment outcomes in TAVR and liver trauma.
problem Improving treatment outcomes in medical procedures.
method Multimodal Prescriptive Neural Networks (PNNs) combining optimization and machine learning.
result PNNs significantly improve estimated outcomes in medical procedures.
DARN uses multiple source datasets to adapt to a new target dataset.
problem Learning a model for a new, related dataset using multiple source datasets.
method DARN applies domain discrepancy minimization with a theoretical generalization bound to adjust source domain weights.
result DARN significantly outperforms state-of-the-art alternatives on real-world datasets.
ROCCO solves Co-Clustering problems efficiently over massive datasets.
problem Simultaneously clustering samples and features in cross-domain datasets.
method Graph-based two-sided representation learning with non-convex optimization.
result ROCCO achieves state-of-the-art performance and is robust to noise.
DNN2LR bridges DNN power and LR interpretability.
problem Combining DNN power and LR interpretability for real-world tabular data.
method Automatic feature crossing method based on DNN interpretation inconsistencies.
result DNN2LR outperforms complex DNN models and feature crossing methods.
Paper tackles activity recognition from body-worn video footage.
problem Classifying frames of body-worn video footage according to the wearer's activity.
method Extract motion features and semi-supervised classification.
result Method achieves comparable results to supervised and deep learning methods using less training data.
Deep learning models struggle with irrelevant features in survival analysis.
problem Deep learning models suffer from performance deficits when dealing with many irrelevant features in survival analysis.
method Developed novel feature selection methods for deep learning models in survival analysis.
result Substantial performance improvements are achievable with feature selection methods.
Adaptive regularization tackles heteroskedastic and imbalanced datasets in deep learning.
problem Heteroskedastic and imbalanced datasets challenge deep learning due to varying label uncertainty and long-tailed label distributions.
method Data-dependent adaptive regularization that applies stronger regularization to higher-uncertainty, lower-density regions.
result Significant improvement in noise-robust deep learning over other methods on benchmark tasks.
Study evaluates methods for improving model robustness to various real-world distribution shifts.
problem Improving model robustness to real-world distribution shifts like geographic changes.
method Introduced new datasets and evaluated existing methods on four types of shifts (style, blurriness, location, camera operation).
result Data augmentations and larger models can improve robustness on real-world distribution shifts, contrary to prior claims.
FairJob dataset for job recommendations in advertising, preserving fairness and utility.
problem Fairness in online job recommendations for advertising.
method Anonymized dataset with proxy for sensitive attributes, fairness metric computation.
result Demonstrated potential improvements in fairness with trade-offs in utility.
New method extracts all reliable linkages in agglomerative clustering.
problem Finding optimal clustering solutions with adaptive and flexible criteria.
method Extracting all reliable linkages at each step for various criteria.
result Single linkage criterion yields minimum spanning tree.
FinDiff generates synthetic financial data for regulatory tasks.
problem Sharing microdata for research due to privacy regulations.
method Diffusion model using embedding encodings for mixed modality financial data.
result FinDiff excels in generating high-fidelity, privacy-preserving synthetic financial data.
Waymo Open Dataset provides a large, diverse, and synchronized LiDAR and camera dataset for autonomous driving research.
problem Limited diversity and scale in existing self-driving datasets hinder real-world problem alignment.
method Developed a new large-scale, high-quality, diverse dataset with synchronized LiDAR and camera data.
result The dataset is 15x more diverse than the largest existing dataset based on a proposed diversity metric.
A new imputation method considers feature importance for missing value completion.
problem Missing values in datasets reduce accuracy and increase processing difficulty.
method Iterative matrix completion with feature importance learning.
result The method outperforms existing imputation algorithms on various datasets.
Discovering causal relationships from data is the ultimate goal of many research areas. Constraint based causal exploration algorithms, such as PC, FCI, RFCI, PC-simple, IDA and Joint-IDA have achieved significant progress and have many applications. A common problem with these methods is the high computational complex…
Evaluates transfer learning methods in dynamic data availability scenarios.
problem Real-world data availability varies over time, leading to unrealistic TL method evaluations.
method Proposes a data manipulation framework to simulate varying data availability and domain transformations.
result Demonstrates the usefulness of the framework on proprietary and publicly available datasets.
This paper introduces a cost-aware feature acquisition method using denoising autoencoders.
problem Optimizing feature acquisition costs in real-world scenarios.
method Incrementally asks for features based on context and uses denoising autoencoders for unknown features.
result The method efficiently acquires features at test-time in a cost- and context-aware fashion.
Enhanced Extended Isolation Forest (EIF+) improves anomaly detection and provides interpretable explanations.
problem Detecting anomalies in complex datasets and explaining model predictions.
method Extended Isolation Forest (EIF) and Extended Isolation Forest Feature Importance (ExIFFI) methods.
result EIF+ outperforms EIF in detecting unseen anomalies and provides better generalization.
Paper tackles domain adaptation for contextual bandits with sub-linear regret.
problem Adapting contextual bandit algorithms across domains with distribution shift.
method Learn a bandit model for the target domain using feedback from the source domain.
result Sub-linear regret bound maintained across domains.
This work tackles costly feature acquisition for classification, using RL.
problem Classification with costly feature acquisition.
method Formulated as a sequential decision-making problem (MDP) and solved with deep reinforcement learning.
result Robust performance across various datasets and settings, outperforming prior-art.
Enhances GNNs for causal relationship learning.
problem Lack of robust causal modeling in GNNs.
method Synthesized dataset with known causal relationships, lightweight GNN module.
result Empirically validated GNN module improves causal learning.
Paper proves mathematically that poisoning datasets can be detected.
problem Detecting data poisoning attacks in datasets.
method Mathematical definition and Conformal Separability Test.
result Dataset poisoning can be effectively detected.
A tool predicts BN performance for real-world datasets.
problem Lack of validation for BN results in real-world applications.
method Synthetic datasets and structure learning algorithms to estimate BN performance.
result Automatic recommendations for BN performance based on synthetic data.
New method detects outliers in correlated data.
problem Detecting outliers in noisy, correlated datasets.
method Robust regression model that detects outliers during model fitting.
result Outlier detection method achieves better performance.
Synthetic data mimics real-world demographics for fairness testing.
problem Lack of complete, representative datasets for fairness testing.
method Construct synthetic datasets using overlapping real and separate datasets.
result Synthetic data yields consistent fairness metrics with real data.
Proposes PUUPL for PUL in imbalanced datasets, boosting minority class signals.
problem Imbalanced datasets and model calibration in PUL.
method Uncertainty-aware pseudo-labeling procedure (PUUPL).
result Substantial performance gains in highly imbalanced settings.
Paper benchmarks real-world noisy labels and proposes a method to improve deep learning performance.
problem Understanding deep learning with real-world noisy labels.
method Develops a simple method to handle both synthetic and real noisy labels.
result Method achieves best results on benchmark datasets and web noise.