paper-with-me

홈 › Papers

Learning Invariant Representations with Missing Data

2021-12-01 · Mark Goldstein, Jörn-Henrik Jacobsen, Olina Chau, Adriel Saporta, Aahlad Puli, Rajesh Ranganath, Andrew C. Miller

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.

📄 PDF Abstract BibTeX arXiv:2112.00881

Code (1)

marikgoldstein/missing-mmd 공식 구현

Similar Papers 제목 키워드 기반

Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach

2024-08-14 · Muhammad Saad Saeed, Shah Nawaz, Muhammad Zaigham Zaheer, Muhammad Haris Khan 외

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

2024-09-28 · Tianyi Liu, Zhaorui Tan, Haochuan Jiang, Xi Yang 외

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 Segmentation

Data-based system representations from irregularly measured data

2023-07-21 · Mohammad Alsalti, Ivan Markovsky, Victor G. Lopez, Matthias A. Müller

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 Completion

Multi-Station WiFi CSI Sensing Framework Robust to Station-wise Feature Missingness and Limited Labeled Data

2026-03-12 · Keita Kayano, Takayuki Nishio, Daiki Yoda, Yuta Hirai 외 arxiv

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 Augmentation

ReMasker: Imputing Tabular Data with Masked Autoencoding

2023-09-25 · Tianyu Du, Luca Melis, Ting Wang

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