Learning Invariant Representations with Missing Data
Spurious correlations allow flexible models to predict well during training but poorly on related test distributions. Recent work has shown that models that satisfy particular independencies involving correlation-inducing \textit{nuisance} variables have guarantees on their test performance. Enforcing such independencies requires nuisances to be observed during training. However, nuisances, such as demographics or image background labels, are often missing. Enforcing independence on just the observed data does not imply independence on the entire population. Here we derive \acrshort{mmd} estimators used for invariance objectives under missing nuisances. On simulations and clinical data, optimizing through these estimates achieves test performance similar to using estimators that make use of the full data.
Code (1)
Similar Papers 제목 키워드 기반
Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach
Multimodal networks have demonstrated remarkable performance improvements over their unimodal counterparts. Existing multimodal networks are designed in a multi-branch fashion that, due to the reliance on fusion strategi…
Mind the Gap: Promoting Missing Modality Brain Tumor Segmentation with Alignment
Brain tumor segmentation is often based on multiple magnetic resonance imaging (MRI). However, in clinical practice, certain modalities of MRI may be missing, which presents an even more difficult scenario. To cope with …
Brain Tumor SegmentationKnowledge DistillationTumor SegmentationData-based system representations from irregularly measured data
Non-parametric representations of dynamical systems based on the image of a Hankel matrix of data are extensively used for data-driven control. However, if samples of data are missing, obtaining such representations beco…
Low-Rank Matrix CompletionMatrix CompletionMulti-Station WiFi CSI Sensing Framework Robust to Station-wise Feature Missingness and Limited Labeled Data
We propose a WiFi Channel State Information (CSI) sensing framework for multi-station deployments that addresses two fundamental challenges in practical CSI sensing: station-wise feature missingness and limited labeled d…
Self-Supervised LearningRepresentation LearningData AugmentationReMasker: Imputing Tabular Data with Masked Autoencoding
We present ReMasker, a new method of imputing missing values in tabular data by extending the masked autoencoding framework. Compared with prior work, ReMasker is both simple -- besides the missing values (i.e., naturall…
ImputationMissing Values