Smote
PulseAugur coverage of Smote — every cluster mentioning Smote across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Feature scaling outperforms deep learning for respiratory screening in low-resource settings
A new study published on arXiv suggests that feature scaling, a common preprocessing technique, can significantly outperform architectural choices in offline respiratory sound classification for low-resource clinics. Re…
-
Quantum SVMs benchmarked for credit card fraud detection
A new research paper explores the effectiveness of Quantum Kernel Support Vector Machines (QSVM) for credit card fraud detection, a task complicated by the rarity of fraudulent transactions. The study benchmarks three q…
-
Deep tabular generative models fail to outperform baselines in benchmark study
A new benchmark study on arXiv investigates the effectiveness of deep tabular generative models compared to simpler baselines. Across 8 public datasets subsampled from 200 to 20,000 rows, and 4 natively small clinical d…
-
AI benchmark audit reveals hidden costs of high accuracy
A new research paper audits the widely used IBM Telco Customer Churn benchmark, revealing significant trustworthiness issues that are often overlooked by standard accuracy and F1-score reporting. The study found that pr…
-
New PU classification method integrates SMOTE for improved accuracy
Researchers have developed a new logistic regression-based approach for PU classification, specifically addressing violations of the SCAR assumption. This method integrates the SMOTE technique to manage class imbalance …
-
New method corrects bias in imbalanced AI learning
Researchers have developed a bias-correction procedure to improve probabilistic classification in imbalanced learning scenarios. This method addresses discrepancies between synthetic and target minority distributions th…
-
Machine learning enhances power system security classification
Researchers have developed a machine learning approach to enhance power system security by classifying contingency scenarios. The study utilized algorithms like Random Forest, Support Vector Machines, and K-Nearest Neig…
-
New SMOTE-VAR method improves AI prediction of depression remission
Researchers have developed a new oversampling method called SMOTE-VAR to improve the accuracy of machine learning models predicting depression remission in university students. Traditional methods like SMOTE can generat…
-
New SMOTE-VAR method improves AI prediction of depression remission in students
Researchers have developed a new oversampling method called SMOTE-VAR to improve the accuracy of machine learning models predicting depression remission in university students. This novel approach uses a Gaussian proces…
-
IJCAI-ECAI 2026 opens, honoring AI pioneers and new research · 1 source tracked
The 35th International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2026) has opened in Bremen, Germany, celebrating significant achievements in the field. Stanford's Jiajun Wu received the prestigious Comput…
-
Study reveals single-dataset evaluations of AI imbalance handling are unreliable
A new study published on arXiv investigates the common practice of evaluating class-imbalance handling methods on a single dataset, demonstrating that conclusions drawn from such limited testing can be misleading. The r…
-
Two new papers propose robust RVFL network variants for noisy data
Two new research papers introduce novel approaches to enhance the robustness of Random Vector Functional Link (RVFL) networks, which are known for their efficiency but susceptibility to noisy data. The first paper, RoBe…
-
New geometric filtering method enhances LLM-generated data for text classification
Researchers have developed a novel geometric filtering framework to improve the quality of synthetic data generated by large language models (LLMs) for text classification tasks. This method evaluates LLM-generated samp…
-
New CISO framework offers per-instance safety guarantees for imbalanced learning
Researchers have developed Certified Interpolation Safe Oversampling (CISO), a novel three-phase framework designed to generate synthetic data instances for imbalanced learning tasks. Unlike traditional methods that foc…
-
B2B e-commerce transaction prediction framework improves precision with DiCE and PyPARC
A new paper introduces a framework for predicting transaction propensity in B2B e-commerce, addressing challenges posed by heterogeneous buyer behaviors that traditional methods like SMOTE struggle with. The proposed ap…
-
New multi-generator GAN improves rare failure detection in predictive maintenance
Researchers have developed a specialized multi-generator Generative Adversarial Network (GAN) to improve the detection of rare failures in predictive maintenance systems. This new approach addresses the limitations of t…
-
New RoBERTa Framework Tackles Class Imbalance in Cybersecurity Vulnerability Classification
A new research paper proposes a Hierarchy-Aware RoBERTa framework to address class imbalance in cybersecurity vulnerability classification using the Common Weakness Enumeration (CWE) taxonomy. The framework explicitly i…
-
Quantum Circuit Born Machines enhance synthetic data generation for imbalanced datasets
Researchers have developed a hybrid quantum-classical framework utilizing Quantum Circuit Born Machines (QCBMs) to generate synthetic data for imbalanced tabular datasets. This approach leverages quantum properties like…
-
New CPAC method boosts fraud detection with improved latent space clustering
Researchers have developed a new method called the Causal Prototype Attention Classifier (CPAC) to improve the detection of fraudulent credit card transactions. This approach addresses the challenge of extreme class imb…
-
Resampling methods degrade model calibration, but recalibration offers a fix
A new research paper published on arXiv explores the impact of resampling methods on the probability calibration of tree ensemble models. The study found that while SMOTE (Synthetic Minority Over-sampling Technique) cau…