Tag
The paper presents a two-part study using machine learning on large-scale telehealth data to classify self-reported chronic kidney disease status and identify key psychosocial and medical predictors, achieving balanced accuracy around 72-76% with SHAP analysis for interpretability.
Presents GAUGE, a lightweight counterfactual gating framework that handles incomplete multimodal inputs by scoring fine-grained evidence units with Taylor approximation and applying continuous gates for reliable prediction.
The paper proposes C²MOE, a Consistency and Complementarity-guided Mixture of Experts framework for incomplete multimodal emotion recognition in conversations, using information-theoretic decomposition to improve robustness when modalities are missing.
This paper proposes Missing-Data Flow Matching, a method that treats missing coordinates of training samples as latent variables and averages the flow matching loss over possible values. Theoretical analysis shows the correction is exact and provides design guidance, with experiments validating the approach on tabular data.
This paper proposes pattern-aware graph neural networks that explicitly encode missingness patterns alongside observed values, achieving an average improvement of 17% in balanced accuracy and 22% in F1-macro across seven UCI datasets.
Proposes CAGI, a framework that integrates clustering and generative adversarial networks to improve missing data imputation by exploiting latent subgroup structures, achieving superior performance on benchmark datasets.
GiFlow is a graph-informed flow matching framework for spatiotemporal imputation that replaces Gaussian priors with a graph-informed prior, and uses a hybrid vector field model combining spatial attention, temporal attention, and spatiotemporal propagation. It outperforms state-of-the-art methods on synthetic and real-world datasets.