IFC-HFlowVAE: A self-enhancing generative framework with structural anchoring for imbalanced clinical data augmentation
- 1School of Big Data & Software Engineering, Chongqing University, Chongqing, China
Abstract
Class imbalance and limited minority-class samples remain major challenges for developing reliable clinical diagnostic models, as insufficient observations often fail to capture complex minority-class distributions. Existing augmentation methods either rely on heuristic interpolation or suffer from instability when learning sparse and heterogeneous medical tabular data. This study proposes IFC-HFlowVAE, an iterative feedback and consensus framework built upon a flow-enhanced heterogeneous variational autoencoder for minority-class data generation. The proposed framework first models mixed-type clinical attributes through HFlowVAE and then introduces a self-circulating refinement strategy to progressively improve generated samples. To alleviate degradation during iterative refinement, SMOTE-generated samples are incorporated as structural references, followed by a localized GMM-based refinement procedure that guides samples toward more representative minority-class regions. Comprehensive experiments on seven clinical tabular datasets demonstrate that IFC-HFlowVAE improves downstream classification performance compared with existing augmentation approaches. Furthermore, fidelity analyses show that the proposed framework better preserves challenging minority-class characteristics, particularly skewed and multimodal numerical distributions.
Related
- Class-Conditioned Diffusion Augmentation and Explainable In-Context Ensemble Learning for Imbalanced Maintenance Action Classification in Aircraft Systems
- Local data augmentation for imbalanced binary classification
- A Generative AI Framework for Structural Analysis and DCGAN-Based Synthesis of Traditional Chinese Papercutting Patterns
- On the Reliability of Generative Augmentation: A Wasserstein-Based Theoretical and Empirical Study
- ML-CLAPPS: A Probabilistic Framework for Imbalanced Multilabel Learning under Class Prioritization
BibTeX
@article{yuwen2026ifchflowvae,
title = {{IFC-HFlowVAE: A self-enhancing generative framework with structural anchoring for imbalanced clinical data augmentation}},
author = {Lu Yuwen and Shuyu Chen},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0357260},
url = {https://doi.org/10.1371/journal.pone.0357260},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - IFC-HFlowVAE: A self-enhancing generative framework with structural anchoring for imbalanced clinical data augmentation
AU - Lu Yuwen
AU - Shuyu Chen
PY - 2026
DA - 2026/09/03
JO - PLOS One
DO - 10.1371/journal.pone.0357260
UR - https://doi.org/10.1371/journal.pone.0357260
AB - Class imbalance and limited minority-class samples remain major challenges for developing reliable clinical diagnostic models, as insufficient observations often fail to capture complex minority-class distributions. Existing augmentation methods either rely on heuristic interpolation or suffer from instability when learning sparse and heterogeneous medical tabular data. This study proposes IFC-HFlowVAE, an iterative feedback and consensus framework built upon a flow-enhanced heterogeneous variational autoencoder for minority-class data generation. The proposed framework first models mixed-type clinical attributes through HFlowVAE and then introduces a self-circulating refinement strategy to progressively improve generated samples. To alleviate degradation during iterative refinement, SMOTE-generated samples are incorporated as structural references, followed by a localized GMM-based refinement procedure that guides samples toward more representative minority-class regions. Comprehensive experiments on seven clinical tabular datasets demonstrate that IFC-HFlowVAE improves downstream classification performance compared with existing augmentation approaches. Furthermore, fidelity analyses show that the proposed framework better preserves challenging minority-class characteristics, particularly skewed and multimodal numerical distributions.
SN - 1932-6203
ER -