Tag
Introduces CALCoDe, a post-hoc reliability layer for frozen medical vision-language models that mitigates class-tail undercoverage under clinical shift, achieving strong worst-class accepted coverage across multiple dermatology shifts and VLM backbones.
Introduces Sharpness-Guided Equilibrium Sampling (SGS) that dynamically adjusts sampling probabilities using sharpness estimates to achieve balanced flat minima in long-tailed learning, achieving significant gains on CIFAR-100 LT and ImageNet-LT.
A federated learning research project reveals that global accuracy can mask catastrophic failure on minority attack classes in network intrusion detection, showing that per-client performance and aggregation method choice are critical for rare attack detection.
This paper compares cascaded and joint multi-task modeling for hierarchical offensive language detection, finding that cascaded architectures achieve higher accuracy at the cost of increased parameters and inference latency, and that class-imbalance handling strategies should be verified via ablation.
Proposes a Hierarchy-Aware RoBERTa framework for classifying cybersecurity vulnerabilities in the CWE taxonomy, demonstrating that hierarchy-aware representation learning is more effective than oversampling techniques for handling class imbalance.
This paper reveals that standard marginal conformal prediction fails to cover minority classes in imbalanced virtual screening datasets, and demonstrates that class-conditional (Mondrian) conformal prediction restores per-class coverage.
The paper proposes FedCGNM, a client-side optimizer that groups classes and normalizes momentum per group to address class imbalance in federated learning, along with FedHOO for efficient hyperparameter exploration. Empirical results show consistent improvements over baselines.
This paper introduces SemiScope, an analysis tool designed to disentangle the effects of classifier tuning from joint SSL and classifier optimization in semi-supervised security classification. Results show that most performance gains attributed to joint optimization can be recovered by simply tuning the classifier and its decision threshold with Bayesian optimization.
Proposes BP-TTA, a test-time adaptation method that handles both class imbalance and continual domain shifts by combining batch-balanced sampling with prototype-guided constraints, achieving state-of-the-art performance in dynamic streaming scenarios.
This paper investigates how training dynamics of neural networks for software defect prediction are affected by coupled data-quality issues such as class imbalance and overlap, proposing an interaction-aware empirical protocol.
Proposes TMR-GGNN, a time-aware multi-relational graph neural network for credit card fraud detection that handles imbalanced data and evolving fraud patterns via contrastive learning and focal loss.
Proposes RGNet, a neural network architecture based on renormalization group theory for hierarchical coarse-graining of feature space to address class imbalance and noise in fault diagnosis. Experimental results on the AI4I dataset show RGNet provides interpretable and competitive performance.
This paper introduces nCMD, a benign-anchored feature selection method for imbalanced network intrusion detection that scores features by deviation from benign class mean, outperforming classical filters on benchmark datasets.
This paper proposes a novel active learning framework that leverages foundation model priors to jointly address class imbalance and label noise, achieving over 50% annotation savings compared to baselines across image and text domains.
This paper presents a hybrid architecture combining FT-Transformer with gradient-boosted trees via calibration-aware stacking for customer churn prediction on structured tabular data, achieving improved F1 and AUC-ROC on a public bank churn dataset.
This paper presents an iterative imbalance-aware fine-tuning approach using Qwen3-8B with QLoRA for psychological defense mechanism classification, achieving a macro F1 of 0.3917 and ranking 4th out of 21 teams in the PsyDefDetect 2026 shared task.
This paper adapts classical class imbalance techniques to Prior-Data Fitted Networks (PFNs) for tabular classification, finding that thresholding and downsampling perform well due to PFNs' calibration and limited-data capabilities.
This paper introduces yvsoucom-iterkit, a deterministic, log-driven AutoML framework for reproducible pipeline optimization in healthcare risk prediction, evaluated on diabetes and stroke datasets with over 18,000 pipeline configurations, achieving strong performance and revealing structured search spaces with component redundancy.
This paper investigates episodic sampling from few-shot learning for class-balanced batch construction in medical image segmentation, showing improved performance under low-data conditions due to reduced overfitting and extended training iterations, with code available on GitHub.
This paper presents a comparative evaluation of classical, ensemble, and neural machine learning approaches for predicting financial distress under severe class imbalance, using SMOTE for oversampling and SHAP for interpretability.