ML-CLAPPS: A Probabilistic Framework for Imbalanced Multilabel Learning under Class Prioritization
Abstract
Real-world datasets often exhibit severe class imbalance, degrading the performance of deep learning models, particularly on rare classes. While imbalance is well studied in binary and multiclass settings, it is substantially more challenging in multilabel problems due to complex label co-occurrence. In clinical applications such as ECG classification, this challenge is coupled with a second critical challenge: the need to prioritize high-risk conditions, regardless of their prevalence, to mitigate the high cost of false negatives. We introduce the Multilabel Class-Prioritized Probabilistic Sampler (ML-CLAPPS), a learnable sampler that optimizes a distribution over training instances to control the model's exposure to different classes. This approach addresses multilabel imbalance while enabling prioritization of significant conditions via a user-defined importance vector (IV). Empirical evaluation on a real-world multilabel ECG image dataset demonstrates that ML-CLAPPS achieves state-of-the-art performance. We show that it aligns class exposure with the specified IV, and that increasing a class's importance leads to corresponding improvements in its classification performance, enabling explicit prioritization of clinically critical conditions.
Related
- GT-PSSM: Unified Probabilistic Framework for Stochastic Dynamics Modeling and Dependency Learning in Multivariate Time Series Anomaly Detection
- IFC-HFlowVAE: A self-enhancing generative framework with structural anchoring for imbalanced clinical data augmentation
- On the Comparison of Optimizers for Imbalanced Learning
- A Fuzzy Adjustment Mechanism to Tune Focal Loss Hyperparameters in Imbalanced Deep Learning
- Bounded Adjustment with Reliability-Guided Embedding for Imbalanced Learning with Noisy Labels
BibTeX
@misc{hazan2026mlclapps,
title = {{ML-CLAPPS: A Probabilistic Framework for Imbalanced Multilabel Learning under Class Prioritization}},
author = {Priel Hazan and Nir Almog and Noam Keidar and Yael Yaniv and Assaf Schuster},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.15816},
eprint = {2610.15816},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.15816},
}
RIS
TY - UNPB
TI - ML-CLAPPS: A Probabilistic Framework for Imbalanced Multilabel Learning under Class Prioritization
AU - Priel Hazan
AU - Nir Almog
AU - Noam Keidar
AU - Yael Yaniv
AU - Assaf Schuster
PY - 2026
DA - 2026/10/11
PB - arXiv
DO - 10.48550/arxiv.2610.15816
UR - https://arxiv.org/abs/2610.15816
AB - Real-world datasets often exhibit severe class imbalance, degrading the performance of deep learning models, particularly on rare classes. While imbalance is well studied in binary and multiclass settings, it is substantially more challenging in multilabel problems due to complex label co-occurrence. In clinical applications such as ECG classification, this challenge is coupled with a second critical challenge: the need to prioritize high-risk conditions, regardless of their prevalence, to mitigate the high cost of false negatives. We introduce the Multilabel Class-Prioritized Probabilistic Sampler (ML-CLAPPS), a learnable sampler that optimizes a distribution over training instances to control the model's exposure to different classes. This approach addresses multilabel imbalance while enabling prioritization of significant conditions via a user-defined importance vector (IV). Empirical evaluation on a real-world multilabel ECG image dataset demonstrates that ML-CLAPPS achieves state-of-the-art performance. We show that it aligns class exposure with the specified IV, and that increasing a class's importance leads to corresponding improvements in its classification performance, enabling explicit prioritization of clinically critical conditions.
ER -