Tag
This paper evaluates self-supervised pretraining for tabular models under label scarcity and missing data, finding mixed efficacy but reliable improvements under test-time missingness.
This paper introduces CAIR, a two-stage framework for imputing physiological time-series data under realistic missingness, outperforming existing methods by incorporating gap mechanisms and curriculum-aware training.
The paper proposes MARCUS, a missing-aware region representation model that treats missing data as contextual urban signals for rent prediction, achieving state-of-the-art performance with significant error reduction on real-world datasets.
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 a Temporal Convolutional Network with symmetric dilation for trajectory inpainting, reconstructing missing segments from observed context using a composite loss function, and evaluates on synthetic 2D trajectories.
This paper studies stochastic linear bandits where the agent only observes a random subset of action coordinates, proving that sublinear regret is possible when actions have low intrinsic dimension, and proposes the TOFU-POV algorithm with theoretical guarantees.
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.
SafeImpute proposes a reliable imputation framework for irregular clinical data using graph neural networks and conformal selection to control the false discovery rate of clinically unacceptable errors.
Presents a diffusion-based approach for generating irregular clinical time series that jointly models laboratory values and their observation patterns, using the DACMI benchmark from MIMIC-III. The model captures clinically meaningful dependencies between patient physiology and testing behavior under MNAR-like missingness.
This paper introduces MedicalRec, a transformer-based recommender system that suggests optimal models for medical image classification tasks without retraining, built on a dataset (MedicalRec-Bench) compiled from 3,000 articles with over 5,000 records.
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.
Proposes ReTAMamba, a method using reliability-aware temporal aggregation with Mamba for irregular clinical time series prediction, achieving significant AUPRC gains on MIMIC-IV, eICU, and PhysioNet 2012.
This paper proposes a two-stage sampling design where LLM evaluations are used to augment, rather than replace, human ratings, and provides guidance on determining sample sizes for human and LLM reviews using a doubly robust estimator from missing data literature.
This paper identifies the problem of missing observations in inverse reinforcement learning (IRL) that can make expert actions appear suboptimal, and develops a practical algorithm to quantify the minimal perturbations needed for expert actions to appear optimal, validated on synthetic tasks, cancer treatment simulation, and ICU data.